© 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. 13241
    Prev
    Next
    INDEX
    Explanations

    count, roll, left, result

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

    The neuron consistently lights up on domain-specific technical or regulatory nouns—especially legal, medical, or commercial terms.

    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
     スカート
    0.74
     monies
    0.73
     humbly
    0.71
     nobility
    0.70
     パンツ
    0.70
     [...]
    0.67
    pendown
    0.66
     boldly
    0.65
    inki
    0.64
     האל
    0.64
    POSITIVE LOGITS
    ᆸ
    0.93
    ఉ
    0.81
    ن
    0.77
     års
    0.75
    అ
    0.75
    ங்கிணை
    0.74
    Coc
    0.74
    스코
    0.73
    र
    0.73
    ᒃ
    0.73
    Activations Density 0.002%

    No Known Activations