© 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. 22-GEMMASCOPE-RES-131K
    7. 67109
    Prev
    Next
    INDEX
    Explanations

    parous, crowdsourcing, skydivers, analysis, dialysis, hemodialysis

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

    terms related to specialized domains, particularly medical, scientific, and technical contexts.

    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_22/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
     Ansatz
    -0.94
     toul
    -0.94
     chrétienne
    -0.94
    itiert
    -0.93
     Perio
    -0.92
    瘢
    -0.91
     intermit
    -0.90
     folyam
    -0.90
     tranf
    -0.90
     توان
    -0.89
    POSITIVE LOGITS
     a
    1.18
     executed
    1.05
     execution
    1.04
     prediction
    0.98
     practice
    0.96
    ออกมา
    0.91
     last
    0.90
     frete
    0.89
     erneut
    0.89
     run
    0.88
    Activations Density 0.133%

    No Known Activations