© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3800
    Prev
    Next
    INDEX
    Explanations

    attribute declarations

    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
    "
    -2.11
    '
    -2.00
    {
    -1.84
    (
    -1.75
     της
    -1.66
    and
    -1.66
     officially
    -1.61
    ;
    -1.49
    的
    -1.48
    rago
    -1.47
    POSITIVE LOGITS
    CodeAttribute
    2.02
    @[+][
    2.02
    ëren
    1.90
    ());
    
    1.85
    ()).
    1.82
    
    1.82
    }}+\
    1.78
    ৹
    1.78
    addCriterion
    1.77
    DoubleQuotes
    1.77
    Activations Density 0.004%

    No Known Activations