© 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. 8019
    Prev
    Next
    INDEX
    Explanations

    location names

    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
     selben
    -3.11
    ’，
    -3.05
     poignant
    -2.81
    欵
    -2.67
    贵族
    -2.36
    先は
    -2.34
    y
    -2.34
     zahlreiche
    -2.34
    谖
    -2.31
     quaint
    -2.28
    POSITIVE LOGITS
    ᛬
    2.64
     IBRARY
    2.53
    麽
    2.47
     ​​
    2.36
    𓍊
    2.33
     were
    2.30
    amp
    2.28
     is
    2.14
    獁
    2.14
     We
    2.13
    Activations Density 0.035%

    No Known Activations