© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129628
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    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
    .;
    -1.11
     “
    -1.05
     if
    -1.03
    .,
    -0.99
    .-
    -0.96
    .:
    -0.94
    '.
    -0.90
    hi
    -0.87
     neue
    -0.87
    ‘
    -0.87
    POSITIVE LOGITS
    laat
    1.02
     symptômes
    0.99
     öde
    0.96
    gefunden
    0.94
    hadapi
    0.94
     รส
    0.94
     dáms
    0.94
     oeufs
    0.93
    bảng
    0.93
     ขาว
    0.93
    Activations Density 0.000%

    No Known Activations