© 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. 73813
    Prev
    Next
    INDEX
    Explanations

    X years after

    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
     to
    -1.49
    éco
    -1.31
    baine
    -1.28
     currently
    -1.27
    的问
    -1.22
    possibly
    -1.21
    为什么会
    -1.21
    俛
    -1.16
     Tuy
    -1.15
    only
    -1.14
    POSITIVE LOGITS
    各種
    1.83
    各种
    1.52
    日常
    1.45
    さまざまな
    1.42
    私は
    1.38
    ｢
    1.38
    Здесь
    1.34
    While
    1.34
    During
    1.33
    There
    1.30
    Activations Density 0.068%

    No Known Activations