© 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. 31-GEMMASCOPE-2-RES-16K
    7. 11744
    Prev
    Next
    INDEX
    Explanations

    end stop punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    Игра
    0.66
    俄罗斯
    0.58
    拙
    0.57
    ≃
    0.54
    英国
    0.54
    Bi
    0.53
    Irish
    0.53
    ¨
    0.52
    conciliation
    0.52
    цкий
    0.52
    POSITIVE LOGITS
    MDEwOlJlcG
    0.66
     monuments
    0.58
     museums
    0.57
     shrugged
    0.56
     cigarettes
    0.55
     subjecting
    0.55
     depots
    0.55
     deposits
    0.54
     Monmouth
    0.54
     thumbnails
    0.54
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.