© 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. 92406
    Prev
    Next
    INDEX
    Explanations

    doctype public declarations

    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
    痪
    -0.75
     Mullins
    -0.70
    getenv
    -0.68
    vidades
    -0.66
    嗔
    -0.65
    férés
    -0.63
    temi
    -0.63
     Comet
    -0.63
     filler
    -0.63
    служи
    -0.63
    POSITIVE LOGITS
     reverber
    0.71
    mLast
    0.68
     Per
    0.67
    adple
    0.66
     '{
    0.66
     Recommended
    0.65
    ání
    0.65
    льня
    0.63
    oop
    0.63
    šč
    0.63
    Activations Density 0.056%

    No Known Activations