© 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. 157364
    Prev
    Next
    INDEX
    Explanations

    undefined constants: arr, child, cat

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

    keywords and punctuation

    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
     ウ
    0.43
     タイプ
    0.41
    ន
    0.41
     マン
    0.41
     ト
    0.40
     ナ
    0.39
     veze
    0.38
     medios
    0.38
     ปี
    0.38
    زب
    0.37
    POSITIVE LOGITS
     consectetur
    0.41
    idunt
    0.39
     छह
    0.38
    marginBottom
    0.38
    calculate
    0.37
    glClear
    0.36
    6
    0.36
    గ్రహ
    0.35
    memset
    0.35
     шрифт
    0.35
    Activations Density 0.077%

    No Known Activations