© 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. 100424
    Prev
    Next
    INDEX
    Explanations

    self-deprecating mistakes and errors

    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
     нравится
    -1.46
    餐廳
    -1.26
     rendimiento
    -1.23
     Лин
    -1.20
    щото
    -1.20
    我們的
    -1.19
    nému
    -1.18
    joj
    -1.18
    昨日の
    -1.17
     farmacé
    -1.16
    POSITIVE LOGITS
     on
    1.49
     will
    1.48
     in
    1.42
     could
    1.34
     solicita
    1.27
     как
    1.23
     didn
    1.17
     have
    1.17
     need
    1.15
     which
    1.13
    Activations Density 0.073%

    No Known Activations