© 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. 71695
    Prev
    Next
    INDEX
    Explanations

    reading input and exceptions

    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
    replyreport
    -3.17
    I
    -3.11
    ſelves
    -2.44
    [
    -2.23
    、「
    -2.16
    ’,
    -2.16
     inventive
    -2.16
    /
    -2.13
     bzw
    -2.11
     ‘‘
    -2.09
    POSITIVE LOGITS
    s
    3.56
    鹇
    2.98
    ization
    2.75
    薷
    2.59
    ౭
    2.50
    ་་
    2.50
    栊
    2.50
    を行い
    2.44
    雠
    2.44
    ression
    2.39
    Activations Density 0.001%

    No Known Activations