© 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. 145341
    Prev
    Next
    INDEX
    Explanations

    checking and conditions

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

    CVE and vulnerability summaries

    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
     usados
    0.55
     використову
    0.54
     usadas
    0.52
    鯖
    0.52
     usado
    0.50
     δύο
    0.50
     ngư
    0.49
     které
    0.49
    人用
    0.49
     ନ
    0.48
    POSITIVE LOGITS
    V
    0.60
    Ō
    0.51
    Women
    0.50
     Women
    0.49
    Russian
    0.49
    Warning
    0.47
    Pascal
    0.47
     J
    0.47
    É
    0.46
    AL
    0.46
    Activations Density 0.000%

    No Known Activations