© 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. 111123
    Prev
    Next
    INDEX
    Explanations

    words with 'dan' or 'den' endings

    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
     jol
    -2.30
    —"
    -2.11
     інші
    -2.03
    挲
    -2.03
    ingly
    -2.03
    wortet
    -2.02
    噌
    -1.98
     "
    -1.95
     свою
    -1.92
     nutzt
    -1.92
    POSITIVE LOGITS
    $
    2.34
    !”
    2.17
    इटम
    2.13
     */
    2.08
    颡
    2.02
    </em>
    1.97
     It
    1.96
    kadang
    1.88
    撰
    1.87
    “
    1.86
    Activations Density 0.001%

    No Known Activations