© 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. 112821
    Prev
    Next
    INDEX
    Explanations

    far beyond expectations

    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
     宣传
    -1.52
     localidades
    -1.47
    ilever
    -1.45
    mathrm
    -1.43
     joyería
    -1.41
    崢
    -1.41
    izare
    -1.40
     firmado
    -1.39
    colore
    -1.35
    biendo
    -1.34
    POSITIVE LOGITS
     -
    1.68
    ON
    1.45
    참고
    1.43
     wygod
    1.37
    aliśmy
    1.31
     rozdí
    1.28
    Klem
    1.27
     its
    1.26
     swoich
    1.26
     neuen
    1.25
    Activations Density 0.021%

    No Known Activations