© 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. 33858
    Prev
    Next
    INDEX
    Explanations

    selection

    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
     Knot
    -0.83
     出来
    -0.82
     galite
    -0.81
     cambian
    -0.81
    口水
    -0.79
    [
    -0.78
     its
    -0.77
    改
    -0.76
     Iterator
    -0.76
     acudi
    -0.75
    POSITIVE LOGITS
    Behind
    1.08
     Behind
    0.97
     자동
    0.83
     Romain
    0.81
    Referências
    0.81
     correspondant
    0.80
     accol
    0.80
     ビキニ
    0.79
     выполнять
    0.79
     sebenarnya
    0.79
    Activations Density 0.254%

    No Known Activations