© 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. 1605
    Prev
    Next
    INDEX
    Explanations

    manual processes and instructions

    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
    ’
    -3.88
     I
    -3.27
     Which
    -2.95
     ซึ่ง
    -2.89
    sandalia
    -2.50
    '
    -2.44
     bizarre
    -2.38
    ↵↵
    -2.38
     
    -2.34
    
    -2.34
    POSITIVE LOGITS
    啣
    3.17
    You
    3.16
    酲
    3.13
    };
    3.09
     setEmail
    3.02
    );
    2.89
    la
    2.88
    ”，
    2.86
    with
    2.77
    悒
    2.77
    Activations Density 0.008%

    No Known Activations