© 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. 153592
    Prev
    Next
    INDEX
    Explanations

    Female residents, removal jobs

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

    conjunctions and punctuation

    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
     cellulose
    0.50
     কোষ
    0.47
     চেহারা
    0.47
     ಕೂದಲ
    0.46
     mũ
    0.46
     ܥ
    0.45
     Fellow
    0.44
     кў
    0.44
    OTROS
    0.44
    Fellow
    0.44
    POSITIVE LOGITS
     It
    0.56
    It
    0.53
    If
    0.52
    وسي
    0.48
     If
    0.48
    While
    0.47
    ർ
    0.47
     While
    0.46
    When
    0.45
    ながら
    0.45
    Activations Density 0.002%

    No Known Activations