© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62541
    Prev
    Next
    INDEX
    Explanations

    license or code headers

    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
    Negative Logits
    mn
    -0.75
    boot
    -0.74
    acia
    -0.73
     userId
    -0.69
     Patent
    -0.69
    userId
    -0.68
    hook
    -0.68
    eq
    -0.68
    month
    -0.68
     foncé
    -0.68
    POSITIVE LOGITS
    镜像
    0.81
    εσ
    0.79
     Decoration
    0.76
    tna
    0.73
    雎
    0.73
     downg
    0.67
    Polish
    0.66
    endalikan
    0.66
    Agre
    0.66
     Ediciones
    0.66
    Activations Density 0.034%

    No Known Activations