© 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. 29938
    Prev
    Next
    INDEX
    Explanations

    certiorari denied or granted

    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
    考える
    -0.69
    biri
    -0.68
     kopling
    -0.68
    orova
    -0.68
     sapere
    -0.68
     agradecer
    -0.67
     Еще
    -0.66
    vitational
    -0.65
    ipi
    -0.64
    kao
    -0.64
    POSITIVE LOGITS
    tides
    0.72
     Kot
    0.70
    Hint
    0.70
     Husband
    0.68
    Pound
    0.66
    大爷
    0.66
    oli
    0.65
    回答
    0.65
    hint
    0.64
     Sc
    0.63
    Activations Density 0.112%

    No Known Activations