© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85493
    Prev
    Next
    INDEX
    Explanations

    silky, brushed, Teflon, satin

    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
     dieß
    -2.66
    霂
    -2.63
    ྵ
    -2.56
    งิน
    -2.45
    kipun
    -2.45
    这个
    -2.44
    这
    -2.42
     ส์
    -2.41
    ”;
    -2.39
    uscany
    -2.39
    POSITIVE LOGITS
    ский
    2.94
     zumindest
    2.52
    i
    2.41
    ні
    2.23
    </b>
    2.17
    ская
    2.17
    頃の
    2.11
    ization
    2.09
    ского
    2.02
    黎明
    1.99
    Activations Density 0.001%

    No Known Activations