© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19434
    Prev
    Next
    INDEX
    Explanations

    programming and user interface elements

    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
    戗
    -2.67
     Перейти
    -2.63
    an
    -2.53
    ;
    
    -2.42
    archiwizowane
    -2.39
     fii
    -2.36
    .";
    
    -2.36
    蛩
    -2.17
    縯
    -2.16
    ⡑
    -2.14
    POSITIVE LOGITS
    玏
    2.61
    他现在
    2.58
    </sup>
    2.50
    fficking
    2.44
    (!)
    2.22
    未だ
    2.19
    íodo
    2.13
    )):
    
    2.08
    </em>
    2.08
    ,:);
    2.05
    Activations Density 0.001%

    No Known Activations