© 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. 47139
    Prev
    Next
    INDEX
    Explanations

    Javascript test exports

    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
     scolaire
    -0.84
     turístico
    -0.83
     through
    -0.83
     térmico
    -0.83
    abung
    -0.83
     rapidly
    -0.82
    dhury
    -0.81
     greatly
    -0.78
     your
    -0.77
    atrician
    -0.75
    POSITIVE LOGITS
     такой
    0.96
    𝗸
    0.90
     такие
    0.85
     تهیه
    0.85
    begle
    0.81
    Blake
    0.80
    После
    0.79
     μας
    0.79
    Especially
    0.79
    ++;
    0.78
    Activations Density 0.002%

    No Known Activations