© 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. 15545
    Prev
    Next
    INDEX
    Explanations

    different, other languages

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

    The neuron fires on references to quantitative facts or statistics—numbers, counts, percentages, or numeric claims.

    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
     и
    0.92
     و
    0.84
     ו
    0.70
     và
    0.70
    z
    0.68
     ও
    0.68
    D
    0.68
     and
    0.67
    0.66
     或
    0.65
    POSITIVE LOGITS
     myös
    0.76
     generell
    0.74
     diğer
    0.70
     également
    0.67
     również
    0.67
     tudi
    0.67
     allgemein
    0.66
    បើ
    0.66
     einzelne
    0.66
     générale
    0.66
    Activations Density 0.000%

    No Known Activations