© 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. 34-GEMMASCOPE-RES-131K
    7. 63520
    Prev
    Next
    INDEX
    Explanations

    file accompanying, CRC Press, factor promoter

    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_34/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
     changé
    -0.77
    颔
    -0.75
    nouveau
    -0.75
    isible
    -0.73
     argent
    -0.72
     dk
    -0.72
     שנים
    -0.72
    tores
    -0.71
    Ohne
    -0.71
     HomeController
    -0.70
    POSITIVE LOGITS
     завдання
    0.73
     drowsiness
    0.69
    خم
    0.67
    ringed
    0.66
    sak
    0.66
     framing
    0.65
     Tid
    0.63
     franc
    0.63
     Muslim
    0.63
    แ
    0.63
    Activations Density 0.052%

    No Known Activations