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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 9497
    Prev
    Next
    INDEX
    Explanations

    links and code structures

    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
     a
    -2.78
    </h5>
    -2.16
    他知道
    -2.06
    ↵
    -1.97
    ↵↵
    -1.97
    s
    -1.88
    ’
    -1.84
     the
    -1.82
     A
    -1.78
    ](
    -1.78
    POSITIVE LOGITS
    </strong>
    2.97
    ógicas
    2.00
    嗐
    1.95
    ACTED
    1.95
    
    1.91
     ISLANDS
    1.85
    洇
    1.84
    вую
    1.84
    otry
    1.80
    л
    1.80
    Activations Density 0.033%

    No Known Activations