© 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. 62637
    Prev
    Next
    INDEX
    Explanations

    work experience

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

    likely cause of common issues

    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
    ;
    0.49
    天
    0.45
    .
    0.45
     rack
    0.44
     and
    0.43
     Lennox
    0.42
     in
    0.42
     b
    0.39
     **
    0.39
     beer
    0.39
    POSITIVE LOGITS
    Telefon
    0.52
     ऑयल
    0.51
    bahan
    0.51
    𒅴
    0.51
     चालक
    0.48
    㞓
    0.48
     전화
    0.47
    㹮
    0.47
    㗆
    0.47
    instrList
    0.46
    Activations Density 0.000%

    No Known Activations