© 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. 91424
    Prev
    Next
    INDEX
    Explanations

    numbers followed by non-digit

    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
     申
    -0.83
     WIL
    -0.81
    aini
    -0.78
    Daddy
    -0.77
     Collins
    -0.74
    waiting
    -0.73
    henswürdigkeiten
    -0.73
    unción
    -0.71
     [*
    -0.71
    Wl
    -0.69
    POSITIVE LOGITS
     vaccine
    0.86
     fehlen
    0.76
     fehlt
    0.76
     मैंने
    0.75
     entsteht
    0.75
     berubah
    0.75
    ců
    0.73
     thiệu
    0.70
     کتاب
    0.70
    Stadium
    0.70
    Activations Density 0.019%

    No Known Activations