© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14918
    Prev
    Next
    INDEX
    Explanations

    organisms

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

    The neuron fires on relatively rare or content‐heavy words (i.e. uncommon, domain-specific tokens) rather than on common function words.

    oai_token-act-pair · o4-miniTriggered 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
     Dus
    0.93
     Holiness
    0.84
     обеспечи
    0.83
     olsa
    0.83
    aclysm
    0.83
    frau
    0.81
    選手権
    0.80
    盻
    0.80
     entspre
    0.79
     entfernt
    0.79
    POSITIVE LOGITS
    Blooming
    0.77
    ش
    0.75
    ات
    0.72
     reporters
    0.70
     organizers
    0.70
    חנו
    0.70
    illing
    0.68
    SEED
    0.68
    ooky
    0.67
    きた
    0.66
    Activations Density 0.000%

    No Known Activations