© 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. 105857
    Prev
    Next
    INDEX
    Explanations

    clothing and names

    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
     you
    -2.86
    ஂ
    -2.47
     and
    -2.47
     seems
    -2.38
     makes
    -2.34
     heartfelt
    -2.33
     was
    -2.31
    >
    -2.31
    
    -2.20
     says
    -2.19
    POSITIVE LOGITS
     spezi
    2.72
    厹
    2.67
     renowned
    2.50
            
    2.47
     revered
    2.33
    *}[
    2.33
    釤
    2.30
     ij
    2.28
     wist
    2.28
     marvelous
    2.23
    Activations Density 0.004%

    No Known Activations