© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 195
    Prev
    Next
    INDEX
    Explanations

    .py configuration files

    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
    \\
    -2.13
    UCIÓN
    -1.81
    imbawa
    -1.78
    ᥬ
    -1.77
    </strong>
    -1.72
     شرکت
    -1.71
    旆
    -1.69
     ""){
    -1.66
     脸
    -1.65
     []);
    -1.64
    POSITIVE LOGITS
     verbess
    2.14
    .’’
    2.13
     demonio
    2.11
     capitulo
    1.95
     it
    1.90
     continúas
    1.82
     celta
    1.80
     ”
    1.80
     sirena
    1.73
    ῞
    1.73
    Activations Density 0.016%

    No Known Activations