© 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. 58398
    Prev
    Next
    INDEX
    Explanations

    Growth, service, hashtag, fire

    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
    론
    -0.78
     Bettina
    -0.78
    comfor
    -0.73
     lance
    -0.72
    rigger
    -0.72
     insulating
    -0.69
     SizedBox
    -0.69
     hearing
    -0.69
     batterie
    -0.68
    盟
    -0.68
    POSITIVE LOGITS
     normalization
    1.18
    normalization
    0.97
    Normalization
    0.95
    GROUPS
    0.93
    Groups
    0.82
     Groups
    0.77
     Roosevelt
    0.75
     supports
    0.75
     relatable
    0.75
     beeintr
    0.75
    Activations Density 0.014%

    No Known Activations