© 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. 79557
    Prev
    Next
    INDEX
    Explanations

    policeman, NBL, comparative evolution

    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
    вор
    -0.79
    ॐ
    -0.74
     Arian
    -0.74
     Devin
    -0.73
    ఉ
    -0.73
     sedu
    -0.72
    arsh
    -0.72
    Analytic
    -0.71
    ふり
    -0.71
     actuated
    -0.71
    POSITIVE LOGITS
     Constraint
    1.12
     constraint
    1.12
    Constraint
    1.01
    Groups
    1.01
    constraint
    1.00
    straint
    0.96
    constraints
    0.96
    groups
    0.94
     GROUPS
    0.91
     Groups
    0.90
    Activations Density 0.009%

    No Known Activations