© 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. 74176
    Prev
    Next
    INDEX
    Explanations

    android phones, movies, gallery

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

    abstract noun phrases

    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
    回収
    0.48
    é
    0.47
    лі
    0.47
    ил
    0.47
    ಗಳಿಗೆ
    0.46
    เต
    0.45
    ور
    0.44
    였다
    0.44
    ले
    0.44
    ê
    0.44
    POSITIVE LOGITS
     Strick
    0.48
     контроль
    0.46
     biopsies
    0.45
     MgII
    0.45
     identificado
    0.44
     والد
    0.43
     Уже
    0.43
    yy
    0.43
    诩
    0.43
    负
    0.42
    Activations Density 0.000%

    No Known Activations