© 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. 87961
    Prev
    Next
    INDEX
    Explanations

    this ticket

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

    local conditions

    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
     optimale
    0.46
     lle
    0.46
     ("/
    0.45
    istika
    0.45
     cua
    0.44
     normalerweise
    0.44
    zed
    0.43
     schnelle
    0.42
    statusCode
    0.41
     koa
    0.41
    POSITIVE LOGITS
    ב
    0.49
    ﾏ
    0.48
    原
    0.47
    펄
    0.47
    书记
    0.46
    ΡΑ
    0.46
    وجد
    0.44
    当地
    0.44
     rumours
    0.44
    origin
    0.44
    Activations Density 0.000%

    No Known Activations