© 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. 66415
    Prev
    Next
    INDEX
    Explanations

    `.py` code and comments

    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
    ֿ
    -0.82
     says
    -0.81
     ressort
    -0.77
     Αρχ
    -0.77
     Teknologi
    -0.76
    stande
    -0.75
    imura
    -0.74
    mAh
    -0.74
     Diptera
    -0.74
    干扰
    -0.73
    POSITIVE LOGITS
    ↵↵↵↵
    1.57
    '],
    1.40
    */
    1.34
    "),
    1.28
    '),
    1.26
    </blockquote>
    1.23
     */
    1.20
     */
    
    1.15
    "],
    1.14
     "),
    1.13
    Activations Density 0.019%

    No Known Activations