© 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. 118435
    Prev
    Next
    INDEX
    Explanations

    telegrams and wires

    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
     biodiesel
    -0.78
    tidaknya
    -0.77
     ネイビー
    -0.73
    柚子
    -0.73
    mış
    -0.73
    rät
    -0.72
     poliester
    -0.72
     يش
    -0.72
    talt
    -0.71
    onSearch
    -0.71
    POSITIVE LOGITS
     telegraph
    2.73
     telegram
    2.61
     tele
    2.52
     cable
    2.33
     wire
    2.23
     wires
    2.09
    telegraph
    1.98
     Telegraph
    1.95
     cables
    1.92
    Tele
    1.90
    Activations Density 0.020%

    No Known Activations