© 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. 65718
    Prev
    Next
    INDEX
    Explanations

    titles, labels, or questions

    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
    ärin
    -0.79
     Notice
    -0.78
    covo
    -0.75
     Antarctic
    -0.71
    andinavian
    -0.71
    czo
    -0.71
     notices
    -0.70
     Gew
    -0.69
    clearInterval
    -0.69
    karz
    -0.69
    POSITIVE LOGITS
    XF
    0.70
    ዊ
    0.66
    爱的
    0.63
     verschw
    0.63
    是以
    0.62
    miyor
    0.62
    攷
    0.61
     XF
    0.60
     Symptom
    0.60
     múltiples
    0.60
    Activations Density 0.068%

    No Known Activations