© 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. 73075
    Prev
    Next
    INDEX
    Explanations

    position or layout keywords

    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
     in
    -1.84
    ;
    -1.72
     or
    -1.48
     There
    -1.45
    共に
    -1.45
     through
    -1.42
    физи
    -1.38
     has
    -1.38
    取締
    -1.36
    逃避
    -1.35
    POSITIVE LOGITS
    在你
    1.56
    多少钱
    1.54
    DockStyle
    1.50
    Niveau
    1.43
    roveň
    1.38
    緜
    1.38
     белой
    1.38
    给他们
    1.34
    くっ
    1.33
    儅
    1.32
    Activations Density 0.001%

    No Known Activations