© 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. 74091
    Prev
    Next
    INDEX
    Explanations

    comedy films and television

    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
    unicaciones
    -2.42
    .’’
    -2.39
    li
    -2.16
    .''
    -2.11
    .""
    -2.05
    N
    -2.05
    ?"
    -2.03
     ''
    -2.02
     AFTER
    -1.98
    .‏
    -1.98
    POSITIVE LOGITS
    .
    2.47
    nue
    2.11
     ontdek
    2.06
    zelfde
    2.02
     étage
    2.00
    屺
    1.96
     wezen
    1.95
    鬭
    1.93
    葙
    1.91
    何度も
    1.87
    Activations Density 0.015%

    No Known Activations