© 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. 34-GEMMASCOPE-RES-131K
    4. 66368
    Prev
    Next
    INDEX
    Explanations

    code closing tags and punctuation

    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_34/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
    ッチリ
    -1.00
    Initializable
    -0.85
     писто
    -0.81
    ഔ
    -0.79
    ットン
    -0.78
    url
    -0.77
     @
    -0.76
    ssin
    -0.75
     шести
    -0.75
     hwnd
    -0.74
    POSITIVE LOGITS
    .);
    0.99
     );
    0.87
    兲
    0.86
     …)
    0.82
    );
    0.81
     taw
    0.81
     温泉
    0.77
    __);
    0.76
    Sü
    0.75
    車両
    0.75
    Activations Density 0.001%

    No Known Activations