© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241394
    Prev
    Next
    INDEX
    Explanations

    City Tour

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    is
    0.61
    d
    0.61
    c
    0.57
    don
    0.54
    dra
    0.54
    m
    0.52
    dı
    0.52
    dolo
    0.52
    dic
    0.51
    dik
    0.51
    POSITIVE LOGITS
    分子
    0.52
     mice
    0.48
    (',');
    0.45
     analyzes
    0.44
     confidently
    0.42
    Đáp
    0.41
    スムーズ
    0.41
    '")
    0.40
    つもり
    0.40
    ᕼ
    0.40
    Activations Density 0.000%

    No Known Activations