© 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. 121419
    Prev
    Next
    INDEX
    Explanations

    letterpress, foil, cotton

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

    regulations, penalties, change, logs

    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
    घाडी
    0.49
    sku
    0.44
    src
    0.43
    暘
    0.43
    ফু
    0.43
    phone
    0.42
     instit
    0.42
    ।"
    0.42
     யு
    0.42
    。[
    0.41
    POSITIVE LOGITS
     letz
    0.47
     الأخيرة
    0.46
     তারাও
    0.46
     northbound
    0.43
    aminate
    0.43
     عنہ
    0.43
     southbound
    0.42
     Systematic
    0.42
     последних
    0.42
     anni
    0.42
    Activations Density 0.000%

    No Known Activations