© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69704
    Prev
    Next
    INDEX
    Explanations

    party events

    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_10/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
    </h2>
    -2.19
    5
    -2.09
     \\
    -1.95
     \
    -1.87
     \"
    -1.86
    7
    -1.81
    8
    -1.81
    instead
    -1.78
    are
    -1.77
    2
    -1.70
    POSITIVE LOGITS
     rendus
    1.76
     prisonniers
    1.73
    czegóły
    1.61
    ƽ
    1.59
    zości
    1.58
    垌
    1.58
     party
    1.55
    各样的
    1.54
     descrito
    1.53
    </b>
    1.52
    Activations Density 0.040%

    No Known Activations