© 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. 32814
    Prev
    Next
    INDEX
    Explanations

    device association

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

    technical terms and calculations

    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
    ja
    0.51
    made
    0.49
    styles
    0.46
    漢字
    0.46
    و
    0.46
    もし
    0.46
    送料
    0.45
    ं
    0.44
    家の
    0.44
    :
    0.44
    POSITIVE LOGITS
     prêt
    0.54
     amus
    0.54
     pesca
    0.54
     administrativo
    0.53
     rooft
    0.53
     utile
    0.53
    aní
    0.53
     acry
    0.52
     biologique
    0.52
    überkü
    0.52
    Activations Density 0.000%

    No Known Activations