© 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. 71342
    Prev
    Next
    INDEX
    Explanations

    passing, surpassing, or exceeding

    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
     is
    -1.82
    の結果
    -1.32
     supreme
    -1.24
    raisers
    -1.13
    就是这样
    -1.13
     azi
    -1.12
     εκεί
    -1.10
     ultimi
    -1.09
    はその
    -1.09
     pensiero
    -1.09
    POSITIVE LOGITS
     Its
    1.34
     andere
    1.31
     plupart
    1.29
     '../
    1.20
    yní
    1.16
    Another
    1.16
    Dlaczego
    1.15
     Each
    1.14
    .</
    1.12
    $)
    1.12
    Activations Density 0.026%

    No Known Activations