© 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. 22-GEMMASCOPE-RES-131K
    7. 27362
    Prev
    Next
    INDEX
    Explanations

    zero followed by punctuation

    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
    Hoog
    -0.96
    Geld
    -0.96
    medel
    -0.95
     EXPEND
    -0.90
    gning
    -0.88
     diente
    -0.88
    下雨
    -0.87
    很快就
    -0.86
     spese
    -0.85
    というわけで
    -0.85
    POSITIVE LOGITS
    TAINER
    0.79
    🍎
    0.79
     Numerous
    0.79
    ()")
    0.78
    :
    0.77
     Архивировано
    0.77
    닛
    0.77
     riddles
    0.76
     ico
    0.76
     Nearly
    0.76
    Activations Density 0.037%

    No Known Activations