© 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. 86942
    Prev
    Next
    INDEX
    Explanations

    highway, Electro, Qin

    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
    Minnesota
    -1.09
     Minnesota
    -0.97
     Minn
    -0.71
     resonant
    -0.70
    Impression
    -0.69
    Amplitude
    -0.69
     Directed
    -0.69
     감
    -0.69
     Prensa
    -0.68
    Etern
    -0.67
    POSITIVE LOGITS
     nacionais
    0.88
     Tamil
    0.82
     kerk
    0.81
     Greenville
    0.81
     ток
    0.79
    andReturn
    0.76
    <%=
    0.75
    回应
    0.75
    ♐
    0.74
    onsumsi
    0.72
    Activations Density 0.014%

    No Known Activations