© 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. 21055
    Prev
    Next
    INDEX
    Explanations

    left ventricular

    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
     был
    -3.06
    \
    -2.80
    寕
    -2.45
    >();
    -2.42
    》：
    -2.23
    "+
    -2.17
    ẋ
    -2.16
    össä
    -2.11
    ;
    -2.09
     Edición
    -2.09
    POSITIVE LOGITS
    y
    3.48
    d
    3.20
    r
    3.11
    derdag
    2.56
    b
    2.44
    薅
    2.39
     использование
    2.33
     was
    2.33
    ről
    2.28
    衕
    2.28
    Activations Density 0.007%

    No Known Activations