© 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. 7086
    Prev
    Next
    INDEX
    Explanations

    fill halfway

    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
    ing
    -1.34
     by
    -1.29
    bbean
    -1.27
    ｏ
    -1.23
     be
    -1.19
    isław
    -1.16
    ة
    -1.15
     hamburger
    -1.14
    手上
    -1.14
     minn
    -1.08
    POSITIVE LOGITS
    nữ
    1.27
    でもいい
    1.15
     Ри
    1.06
     Verkä
    1.06
     Mice
    1.05
    很赞
    1.05
    oulders
    1.05
     chimie
    1.04
    đại
    1.04
    bản
    1.03
    Activations Density 0.021%

    No Known Activations