© 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. 228839
    Prev
    Next
    INDEX
    Explanations

    the work of your fingers

    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
    滥
    0.50
    ăţ
    0.50
    主管部门
    0.48
    що
    0.45
    管理员
    0.44
    $=
    0.44
    steiger
    0.43
    砻
    0.43
    ˆ
    0.43
    л
    0.42
    POSITIVE LOGITS
    subscription
    0.54
     ਇਸ
    0.54
     visionary
    0.52
    Cyber
    0.50
    connection
    0.49
     બીજા
    0.49
    CE
    0.49
    MAP
    0.49
     Cyber
    0.49
    NOR
    0.48
    Activations Density 0.000%

    No Known Activations