© 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. 22-GEMMASCOPE-RES-131K
    7. 129277
    Prev
    Next
    INDEX
    Explanations

    football defender

    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
     ("
    -1.21
     hikay
    -1.20
    ',
    -1.15
    chaik
    -1.13
     "
    -1.12
    诋
    -1.08
     biochemistry
    -1.07
     food
    -1.05
    माण
    -1.03
     ходить
    -1.03
    POSITIVE LOGITS
     defensive
    1.15
    vemos
    1.13
     defence
    1.12
    weds
    1.11
    viously
    1.10
    peka
    1.09
    gering
    1.07
    盦
    1.05
     sequência
    1.05
    gered
    1.05
    Activations Density 0.012%

    No Known Activations