© 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. 152567
    Prev
    Next
    INDEX
    Explanations

    common collocations

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

    keyword difficulty

    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
    Type
    0.48
     sûr
    0.46
    譯
    0.44
     taxonom
    0.44
    ও
    0.44
     taxpayer
    0.43
    도
    0.43
    ა
    0.42
     zusammen
    0.41
     Estud
    0.41
    POSITIVE LOGITS
     exerted
    0.49
    abela
    0.46
    apadani
    0.46
     घाट
    0.46
     हमरे
    0.45
    hid
    0.43
     NOVEMBER
    0.41
     PRIVATE
    0.41
    。
    0.41
    dengan
    0.41
    Activations Density 0.000%

    No Known Activations