© 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. 10-GEMMASCOPE-RES-131K
    7. 14974
    Prev
    Next
    INDEX
    Explanations

    S and following programming code

    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
    趼
    -3.25
    quelize
    -2.95
    獁
    -2.83
     itſelf
    -2.75
    t
    -2.73
    㐂
    -2.73
    ścioła
    -2.67
     asma
    -2.67
    劊
    -2.66
    后续
    -2.64
    POSITIVE LOGITS
    缡
    2.86
    苙
    2.80
     '
    2.73
     пять
    2.66
     realmente
    2.63
     REALLY
    2.61
     nhưng
    2.59
    ('
    2.59
    %;
    2.56
    "
    2.52
    Activations Density 0.021%

    No Known Activations