© 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. 65266
    Prev
    Next
    INDEX
    Explanations

    and the, on Tuesday

    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
     ألف
    -0.71
    Arkansas
    -0.68
    gabri
    -0.68
    dá
    -0.67
    кура
    -0.66
    única
    -0.66
     selepas
    -0.65
    kose
    -0.65
    读者
    -0.65
     quieran
    -0.65
    POSITIVE LOGITS
     ساح
    1.02
     образом
    0.81
     vlak
    0.80
     CCL
    0.78
    тельством
    0.75
    ੀ
    0.75
    calaureate
    0.75
     Matta
    0.75
    ieniu
    0.74
    ⏯
    0.73
    Activations Density 0.020%

    No Known Activations