© 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. 93819
    Prev
    Next
    INDEX
    Explanations

    code or technical terms

    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
    tothe
    -0.73
     باز
    -0.69
    belongs
    -0.69
    putting
    -0.68
     nekaj
    -0.68
     デニム
    -0.67
    Schul
    -0.67
    told
    -0.66
    placing
    -0.66
    ufes
    -0.66
    POSITIVE LOGITS
    adamente
    0.73
     mildly
    0.73
     倍
    0.71
    setFilter
    0.69
     completas
    0.69
     Вікіпе
    0.69
    getJob
    0.69
     completely
    0.68
    athy
    0.68
    小组
    0.68
    Activations Density 0.066%

    No Known Activations