© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7973
    Prev
    Next
    INDEX
    Explanations

    code block end markers

    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
     has
    -2.31
     will
    -2.09
    );
    -2.09
    ！」
    -1.83
    (!__
    -1.78
    AutoModerator
    -1.77
    },
    -1.76
    𓆟
    -1.76
     may
    -1.75
    __":
    -1.73
    POSITIVE LOGITS
    惊艳
    1.83
    慚
    1.78
     น้ำ
    1.76
    嘁
    1.74
    鲥
    1.73
    觚
    1.71
     redak
    1.70
    
    1.70
    鲩
    1.69
     eſſ
    1.68
    Activations Density 0.001%

    No Known Activations