© 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. 200350
    Prev
    Next
    INDEX
    Explanations

    parentheses and enclosing content

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

    lists of items or numbers

    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
    Modern
    0.45
     وول
    0.45
    对象的
    0.44
    层的
    0.43
    대의
    0.43
    y
    0.43
    ^{-\
    0.42
    lerinin
    0.42
    ើ
    0.42
    学生的
    0.42
    POSITIVE LOGITS
     midfielders
    0.54
     utilisateur
    0.52
     divent
    0.52
     deviennent
    0.52
     viennent
    0.49
    นะคะ
    0.49
     decentral
    0.48
     twor
    0.48
     interrelated
    0.48
     jurisdiction
    0.47
    Activations Density 0.000%

    No Known Activations