© 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. 69462
    Prev
    Next
    INDEX
    Explanations

    asking how or whether

    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
    </strong>
    -1.52
    火影
    -1.48
    ('');
    -1.39
    DJANGO
    -1.38
     maceta
    -1.34
    شفى
    -1.34
    ylvanian
    -1.33
    JsonPropertyName
    -1.30
     then
    -1.30
     extracción
    -1.27
    POSITIVE LOGITS
    TAI
    1.17
     regal
    1.14
     occident
    1.14
    立马
    1.13
     glor
    1.13
     rotund
    1.09
    щему
    1.09
     before
    1.09
     לעשות
    1.08
     pois
    1.07
    Activations Density 0.089%

    No Known Activations