© 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. 175544
    Prev
    Next
    INDEX
    Explanations

    Everest base camp

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

    via SSH

    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
    Efficient
    0.54
    efficient
    0.49
    hetes
    0.47
    詞
    0.47
    $，
    0.46
     inefficient
    0.44
    考え
    0.43
    $.}
    0.43
    役割
    0.43
     ngừa
    0.43
    POSITIVE LOGITS
    葲
    0.52
     traff
    0.46
     پیک
    0.46
     رکھیں
    0.46
     طبی
    0.45
     ED
    0.45
     extern
    0.44
     বোল
    0.44
    iliği
    0.44
     بدی
    0.43
    Activations Density 0.000%

    No Known Activations