© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39379
    Prev
    Next
    INDEX
    Explanations

    selection of players

    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_22/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
    lais
    -1.03
    サミ
    -1.00
    เจ้า
    -0.98
     sấy
    -0.95
    <
    -0.94
     típus
    -0.93
    ystemet
    -0.90
    骑士
    -0.90
    0
    -0.90
     colocar
    -0.90
    POSITIVE LOGITS
     lineup
    1.31
     roster
    1.23
     SELECTION
    1.17
     uyt
    1.13
     assembled
    1.13
     who
    1.13
     esqueleto
    1.12
     INCLUDING
    1.11
     museu
    1.09
    鶺
    1.08
    Activations Density 0.027%

    No Known Activations