© 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. 231871
    Prev
    Next
    INDEX
    Explanations

    average from

    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
    anh
    0.49
    as
    0.49
     红
    0.49
     切り
    0.47
    an
    0.46
    in
    0.46
     دل
    0.45
     כל
    0.45
    Indexer
    0.45
     ان
    0.44
    POSITIVE LOGITS
     metade
    0.48
     malnourished
    0.46
     necessitating
    0.45
     visitation
    0.45
     underwent
    0.44
     Controversy
    0.44
    বধ
    0.43
    រស
    0.43
    ローバル
    0.43
    េស
    0.43
    Activations Density 0.000%

    No Known Activations