© 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. 42046
    Prev
    Next
    INDEX
    Explanations

    shaving and sutures

    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
    頻繁
    -2.67
     ominous
    -2.53
     workings
    -2.50
    …」
    -2.47
    ቭ
    -2.45
    
    -2.41
     sizzling
    -2.41
    毟
    -2.36
    ization
    -2.34
    ."—
    -2.34
    POSITIVE LOGITS
     เมื่อ
    2.67
    </b>
    2.48
    镚
    2.44
     et
    2.42
    0
    2.41
    </td>
    2.38
    เพราะ
    2.28
     ไม่
    2.20
     quando
    2.17
     где
    2.17
    Activations Density 0.019%

    No Known Activations