© 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. 96926
    Prev
    Next
    INDEX
    Explanations

    award, away, back, day, not, suppress, template, to, you, your

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

    Hydrogen peroxide, immediately prevents

    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
    os
    0.52
    zcz
    0.47
    Left
    0.45
     tym
    0.45
     adverse
    0.45
    日本語
    0.45
     upsets
    0.44
    ת
    0.44
    {:
    0.43
    とめ
    0.43
    POSITIVE LOGITS
    kao
    0.48
     મો
    0.48
     फैक्ट्री
    0.47
    ,,,
    0.46
     कुलकर्णी
    0.46
    incott
    0.46
    akad
    0.46
     Funktion
    0.45
    蝣
    0.45
     કેવી
    0.45
    Activations Density 0.000%

    No Known Activations