© 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. 99669
    Prev
    Next
    INDEX
    Explanations

    moved to

    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
    e
    -3.23
    k
    -2.77
     några
    -2.47
    ৪
    -2.42
    餮
    -2.39
    ⮜
    -2.28
    ными
    -2.23
     например
    -2.23
     остальные
    -2.22
    呖
    -2.13
    POSITIVE LOGITS
    .
    2.66
    痦
    2.56
    of
    2.52
    '
    2.45
    我很
    2.45
     ツリー
    2.42
     They
    2.39
    乆
    2.39
    ness
    2.23
     แต่
    2.23
    Activations Density 0.006%

    No Known Activations