© 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. 1266
    Prev
    Next
    INDEX
    Explanations

    technical terms separated by 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_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
    ing
    -2.30
    ?
    -2.28
    );
    -2.22
     For
    -2.14
     
    -2.00
     Oft
    -1.95
     Because
    -1.88
    \
    -1.87
     gemäß
    -1.86
     anstatt
    -1.86
    POSITIVE LOGITS
    踅
    2.19
    馘
    2.14
     abiye
    2.09
    麪
    2.09
    蹋
    2.05
     trajets
    1.98
    檍
    1.98
    谖
    1.94
     symptômes
    1.89
    焢
    1.89
    Activations Density 0.001%

    No Known Activations