© 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. 72641
    Prev
    Next
    INDEX
    Explanations

    headings and initial words

    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
     Nascimento
    -0.86
     Tất
    -0.84
     couverts
    -0.83
     деца
    -0.82
    Ainda
    -0.81
    Apesar
    -0.81
    Очень
    -0.81
    樱花
    -0.80
     Ngoài
    -0.79
    Уже
    -0.78
    POSITIVE LOGITS
     初
    0.86
    新的
    0.78
    “
    0.78
    itosti
    0.77
    THE
    0.75
     trabajan
    0.75
    についての
    0.74
     Commentary
    0.73
    <h1>
    0.72
    仰
    0.72
    Activations Density 0.158%

    No Known Activations