© 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. 94218
    Prev
    Next
    INDEX
    Explanations

    json data and structures

    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
     Ende
    -0.86
    versiti
    -0.85
     userRepository
    -0.84
     dioses
    -0.83
     userDao
    -0.77
    removeFrom
    -0.77
     bersi
    -0.76
     their
    -0.76
     Toussaint
    -0.76
     labdar
    -0.76
    POSITIVE LOGITS
     data
    2.56
    data
    2.03
     results
    1.92
     result
    1.82
     payload
    1.63
    payload
    1.55
    Payload
    1.54
     content
    1.52
     records
    1.47
    result
    1.46
    Activations Density 0.017%

    No Known Activations