© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1574
    Prev
    Next
    INDEX
    Explanations

    Yanukovych or father/parents

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects numeric tokens—numbers and numerical data in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to specific competitive events, games, or matches in sports and politics.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    news-style nouns denoting competitive sports outcomes/standings and formal political or governmental actions and entities.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nonfiction
    0.84
     any
    0.79
     unfiltered
    0.75
     many
    0.70
     various
    0.70
     examples
    0.68
     singular
    0.68
     fictional
    0.68
     prototypical
    0.68
     specific
    0.67
    POSITIVE LOGITS
     बुधवार
    0.75
    anwhile
    0.68
     hurriedly
    0.66
     शनिवार
    0.66
     বুধবার
    0.66
     Rabu
    0.65
     Hoping
    0.64
     गुरुवार
    0.64
     शुक्रवार
    0.63
     setempat
    0.63
    Activations Density 0.000%

    No Known Activations