© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91521
    Prev
    Next
    INDEX
    Explanations

    in compliance with

    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
    格兰
    -0.83
    <?=$
    -0.77
     probabilidad
    -0.73
     vya
    -0.71
    該当
    -0.67
    żo
    -0.67
     oggi
    -0.67
    pera
    -0.66
    lamento
    -0.66
    ガール
    -0.66
    POSITIVE LOGITS
    endar
    0.71
    责任编辑
    0.69
     fuentes
    0.69
     dziecię
    0.68
    annels
    0.68
    жды
    0.67
     redeemed
    0.66
    บอล
    0.66
    悟
    0.65
    aneous
    0.65
    Activations Density 0.129%

    No Known Activations