© 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. 41947
    Prev
    Next
    INDEX
    Explanations

    Marvel Cinematic Universe and Comics

    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
    ).
    -2.70
    􀂃
    -2.61
    "
    -2.61
    ";
    -2.42
     bumpy
    -2.34
    と言われる
    -2.14
     flurry
    -2.08
    ↵↵
    -2.05
    については
    -2.02
    );
    -2.00
    POSITIVE LOGITS
    寕
    2.94
    
    2.81
    
    2.80
    ⃨
    2.66
    ﯼ
    2.61
    ”،
    2.61
    鲽
    2.61
    /
    2.59
    ⽥
    2.55
     élevés
    2.52
    Activations Density 0.002%

    No Known Activations