© 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. 2446
    Prev
    Next
    INDEX
    Explanations

    template definitions

    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
     Fro
    -0.82
    acci
    -0.71
     set
    -0.66
    fromCharCode
    -0.65
     FOX
    -0.63
    тию
    -0.63
    时刻
    -0.62
    bido
    -0.62
    スク
    -0.61
    スピ
    -0.60
    POSITIVE LOGITS
    ovr
    0.70
    Shred
    0.66
    Lak
    0.65
    Lateral
    0.63
    pekte
    0.63
    tető
    0.63
     stary
    0.63
    Ѷ
    0.63
    を与える
    0.62
     escova
    0.62
    Activations Density 0.099%

    No Known Activations