© 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. 99976
    Prev
    Next
    INDEX
    Explanations

    cate and spatio-temporal contexts

    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
    狁
    -3.63
     Lately
    -3.25
    }$
    -2.89
     Technically
    -2.86
     Previously
    -2.81
     Mainly
    -2.75
     Already
    -2.69
     Hmm
    -2.67
     Roughly
    -2.64
    味的
    -2.63
    POSITIVE LOGITS
    ၜ
    2.78
    菝
    2.53
    噐
    2.52
    ⬮
    2.47
    𐑂
    2.39
     verdens
    2.34
    AdvEx
    2.33
    يست
    2.31
    Hanya
    2.31
    ⃚
    2.28
    Activations Density 0.006%

    No Known Activations