© 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. 2681
    Prev
    Next
    INDEX
    Explanations

    group and gid identifiers

    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
     проживания
    -0.78
     என்ற
    -0.77
     年
    -0.75
     infinity
    -0.72
     money
    -0.69
    本の
    -0.69
    مول
    -0.68
    鳳
    -0.68
    덟
    -0.68
    ΡΟ
    -0.68
    POSITIVE LOGITS
     groups
    1.58
     group
    1.48
    gid
    1.34
    Groups
    1.33
     Groups
    1.32
    group
    1.31
     Group
    1.29
    groups
    1.28
     GROUPS
    1.23
     گروه
    1.20
    Activations Density 0.054%

    No Known Activations