© 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. 48181
    Prev
    Next
    INDEX
    Explanations

    code syntax

    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
    for
    -2.88
    3
    -2.86
    0
    -2.67
    a
    -2.63
    e
    -2.59
    </h4>
    -2.56
    Two
    -2.47
    --
    -2.45
    }
    -2.45
    d
    -2.41
    POSITIVE LOGITS
     aisladas
    2.53
    釙
    2.47
    
    2.38
    
    2.36
    咴
    2.33
     cercanas
    2.31
     mismos
    2.25
     diseñ
    2.22
    ⽐
    2.19
    sandalia
    2.14
    Activations Density 0.003%

    No Known Activations