© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 178108
    Prev
    Next
    INDEX
    Explanations

    cities and regions

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

    categorized by strengths

    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
     Indications
    0.46
    Endpoints
    0.45
    Price
    0.45
    ずっと
    0.45
    女
    0.44
    வில்லை
    0.44
    త్రి
    0.43
    ளமான
    0.43
     Restrictions
    0.43
    üre
    0.43
    POSITIVE LOGITS
     gras
    0.49
     cuidado
    0.49
     werden
    0.48
     æ
    0.46
    ний
    0.45
     écrit
    0.45
    اً
    0.45
     classe
    0.44
     لکھ
    0.44
     इत्या
    0.43
    Activations Density 0.000%

    No Known Activations