© 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. 47203
    Prev
    Next
    INDEX
    Explanations

    data type definitions

    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
    allar
    -0.85
    tovní
    -0.83
     consentement
    -0.83
     tamam
    -0.83
     віта
    -0.81
     ENGINEERS
    -0.79
     oleju
    -0.79
     Brasile
    -0.78
    struk
    -0.77
    juh
    -0.77
    POSITIVE LOGITS
    repeated
    0.99
     repeated
    0.95
     string
    0.95
    string
    0.90
     bool
    0.88
     uint
    0.85
     entgeg
    0.85
    Singular
    0.82
    sint
    0.80
    ostasis
    0.79
    Activations Density 0.002%

    No Known Activations