© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111543
    Prev
    Next
    INDEX
    Explanations

    not understanding or not working

    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
    䉴
    -2.95
     constater
    -2.92
     accompagner
    -2.91
    횃
    -2.86
     occuper
    -2.81
     variante
    -2.75
     distinguer
    -2.72
     cosmé
    -2.70
    呖
    -2.69
    sivité
    -2.66
    POSITIVE LOGITS
    ↵
    2.66
     is
    2.55
     he
    2.42
    <i>
    2.30
    </b>
    2.11
    {
    2.06
     teniendo
    2.05
    にしました
    2.05
    啻
    2.03
     necessarily
    1.98
    Activations Density 0.002%

    No Known Activations