© 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. 44016
    Prev
    Next
    INDEX
    Explanations

    page counts

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

    number of pages

    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
    趁
    0.46
    toire
    0.45
    клика
    0.43
    爣
    0.42
     పొంద
    0.41
    璋
    0.41
    倜
    0.41
    霈
    0.40
     일어나
    0.40
    রান
    0.39
    POSITIVE LOGITS
     rows
    0.45
    en
    0.45
     cartoons
    0.45
     Sade
    0.44
     gills
    0.44
    upper
    0.43
     குற்றம்
    0.43
     upper
    0.42
     Kum
    0.41
     Ci
    0.41
    Activations Density 0.008%

    No Known Activations