© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15366
    Prev
    Next
    INDEX
    Explanations

    menu, subtitle, and categories

    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
    </strong>
    -1.42
     They
    -1.40
     Their
    -1.39
     Ayrıca
    -1.38
     inmiddels
    -1.34
    THE
    -1.34
    ₅
    -1.33
    не
    -1.30
    ┅
    -1.29
    </em>
    -1.27
    POSITIVE LOGITS
    れたら
    1.65
    のほうが
    1.55
     sonidos
    1.55
    抡
    1.53
    苼
    1.51
    𓆉
    1.51
    巔
    1.48
    Ꭳ
    1.48
     lecteur
    1.46
     своих
    1.45
    Activations Density 0.018%

    No Known Activations