© 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. 22-GEMMASCOPE-RES-131K
    7. 33128
    Prev
    Next
    INDEX
    Explanations

    code variable names

    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_22/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
    новременно
    -0.85
    就會
    -0.84
    rī
    -0.82
     then
    -0.81
     which
    -0.80
    nodata
    -0.76
    rası
    -0.76
     として
    -0.76
    以外の
    -0.75
     ところ
    -0.75
    POSITIVE LOGITS
     to
    1.16
    芪
    0.97
     tecnologías
    0.96
     kovo
    0.94
     Tienen
    0.92
     corregir
    0.92
    ggish
    0.91
    とは言
    0.91
    了好
    0.90
    rille
    0.90
    Activations Density 0.012%

    No Known Activations