© 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. 37749
    Prev
    Next
    INDEX
    Explanations

    people's names and titles

    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
    それにしても
    -0.81
    了我
    -0.78
     刀
    -0.76
     Complementary
    -0.75
    𝓂
    -0.71
    тельных
    -0.69
     deutlich
    -0.69
     distinguish
    -0.69
    这件事
    -0.68
    andosi
    -0.68
    POSITIVE LOGITS
    валя
    0.90
     hale
    0.90
     Ше
    0.83
     Datos
    0.81
    aaral
    0.79
    vimos
    0.78
    BITE
    0.77
     skla
    0.77
    nahm
    0.75
     redak
    0.74
    Activations Density 0.033%

    No Known Activations