© 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. 106331
    Prev
    Next
    INDEX
    Explanations

    user role level

    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
    득
    -0.81
     involunt
    -0.80
    ticing
    -0.79
     tene
    -0.77
     pname
    -0.77
    こんばんは
    -0.76
     jil
    -0.76
     miniatur
    -0.76
    ficial
    -0.75
     perifer
    -0.75
    POSITIVE LOGITS
     role
    2.58
     roles
    2.16
     Role
    2.05
    role
    1.82
    Role
    1.78
     Roles
    1.70
     level
    1.67
     privileges
    1.64
     type
    1.63
     privilege
    1.58
    Activations Density 0.011%

    No Known Activations