© 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. 74913
    Prev
    Next
    INDEX
    Explanations

    Marvel characters and actors

    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
    /
    -2.64
    彣
    -2.34
     But
    -2.27
    \
    -2.19
    Aujourd
    -2.03
     cejas
    -2.03
    referer
    -1.99
     教室
    -1.98
    9
    -1.98
    齪
    -1.97
    POSITIVE LOGITS
     colocando
    2.63
     deixando
    2.50
    なって
    2.33
     cuyas
    2.16
    鸶
    2.14
    ᯾
    2.13
    频繁
    2.09
     gráfica
    2.09
    例の
    2.08
    刄
    2.06
    Activations Density 0.001%

    No Known Activations