© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1849
    Prev
    Next
    INDEX
    Explanations

    et al

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     otherwise
    -0.79
     actually
    -0.77
    ecutable
    -0.77
     credits
    -0.76
    享受
    -0.71
    Cdb
    -0.68
     vang
    -0.67
    割合
    -0.67
    ってこと
    -0.67
     next
    -0.66
    POSITIVE LOGITS
     al
    2.58
    etal
    1.17
     др
    1.15
     collaborators
    1.14
     alk
    1.11
     alre
    1.09
     аль
    1.05
     např
    1.00
    アル
    0.99
     all
    0.97
    Activations Density 0.041%

    No Known Activations