© 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. 73304
    Prev
    Next
    INDEX
    Explanations

    display block or hidden

    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
     telefónica
    -0.92
    kig
    -0.88
     when
    -0.86
    Kino
    -0.83
    Tambah
    -0.83
     diterapkan
    -0.83
    amanan
    -0.80
    ittoria
    -0.77
    govt
    -0.77
    két
    -0.77
    POSITIVE LOGITS
    艸
    0.86
     SOMEONE
    0.84
     indic
    0.83
    Если
    0.82
     veau
    0.81
     este
    0.81
    Mesmo
    0.81
     couteau
    0.80
     quatrième
    0.77
    悪魔
    0.77
    Activations Density 0.004%

    No Known Activations