© 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. 10-GEMMASCOPE-RES-131K
    7. 10141
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and 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_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
    5
    -2.03
    7
    -1.86
     will
    -1.84
    8
    -1.83
    6
    -1.82
     or
    -1.77
    9
    -1.69
    pende
    -1.67
    今朝
    -1.63
    0
    -1.59
    POSITIVE LOGITS
    new
    1.78
    嘮
    1.70
    циях
    1.68
     ögon
    1.68
     sieben
    1.68
     ursprünglich
    1.65
    撵
    1.61
    aabb
    1.60
    ՙ
    1.59
    AJAS
    1.55
    Activations Density 0.095%

    No Known Activations