© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 73366
    Prev
    Next
    INDEX
    Explanations

    util followed by punctuation

    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
     badly
    -0.77
     кстати
    -0.74
     cleaner
    -0.73
     Herrmann
    -0.71
    cleaner
    -0.71
     asos
    -0.70
    newArrayList
    -0.69
    わん
    -0.69
     kada
    -0.69
     HOTEL
    -0.68
    POSITIVE LOGITS
    ERGY
    0.74
    明星
    0.69
    金山
    0.68
    holz
    0.66
     verses
    0.66
    チャート
    0.66
    ardia
    0.65
     queues
    0.65
    erir
    0.64
    iksi
    0.64
    Activations Density 0.037%

    No Known Activations