© 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. 15032
    Prev
    Next
    INDEX
    Explanations

    Mecca, Schur, PDE, Dix

    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
    ⎆
    -2.61
    ﹔
    -2.23
    Getting
    -2.16
                    
    -2.11
    ⤒
    -2.09
    庒
    -2.02
    錳
    -2.00
    ଽ
    -2.00
    說
    -2.00
    郸
    -1.98
    POSITIVE LOGITS
    ve
    2.50
    ’
    2.36
    灩
    2.33
    肫
    2.22
     Mungkin
    2.08
    2
    2.03
     \'
    2.02
     incre
    2.02
     we
    2.02
     andere
    1.98
    Activations Density 0.029%

    No Known Activations