© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77172
    Prev
    Next
    INDEX
    Explanations

    functional anatomy

    np_acts-logits-general · gemini-2.5-flash-lite

    programming or code-related content, especially in files with indentation and technical syntax.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Tav
    -0.79
    baut
    -0.73
     Reise
    -0.73
     septiembre
    -0.72
    otriz
    -0.71
    recover
    -0.71
    bley
    -0.69
     nommée
    -0.69
    camy
    -0.69
     recovers
    -0.68
    POSITIVE LOGITS
     Convex
    0.70
     Yü
    0.70
     conduite
    0.67
    стью
    0.66
     desu
    0.66
     aile
    0.65
     asim
    0.63
     CSRF
    0.62
     crests
    0.62
     Mortality
    0.61
    Activations Density 0.047%

    No Known Activations