© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2390
    Prev
    Next
    INDEX
    Explanations

    playing roles

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ionale
    -0.95
     can
    -0.90
    Winds
    -0.84
     for
    -0.81
     schon
    -0.79
     after
    -0.79
     evaporator
    -0.79
    ‌پدی
    -0.78
    文件名
    -0.77
     ζωή
    -0.76
    POSITIVE LOGITS
     roles
    1.29
     role
    1.25
    role
    1.06
    Role
    1.05
    Roles
    1.04
     voice
    0.99
    UserRole
    0.98
    roles
    0.94
     rôle
    0.93
     Roles
    0.93
    Activations Density 0.008%

    No Known Activations