© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 94126
    Prev
    Next
    INDEX
    Explanations

    stackexchange.com or stackoverflow.com

    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
     category
    -0.73
    lund
    -0.72
     Blick
    -0.69
    setLeft
    -0.69
     Attorney
    -0.69
     gram
    -0.69
    Gram
    -0.68
     مات
    -0.68
     DS
    -0.68
     Mau
    -0.68
    POSITIVE LOGITS
     Severn
    0.75
     furt
    0.72
    ーリー
    0.72
     گزارش
    0.71
     Sya
    0.71
     syndic
    0.67
    ᄅ
    0.67
     simpl
    0.67
    bericht
    0.66
    툰
    0.66
    Activations Density 0.050%

    No Known Activations