© 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. 1184
    Prev
    Next
    INDEX
    Explanations

    Am J Physiol, Heart J, Medical Association

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

    academic journal citations and references.

    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
    Poh
    -0.85
     bile
    -0.77
    ナルド
    -0.76
    starred
    -0.73
     گردد
    -0.73
    dialogs
    -0.71
    тую
    -0.70
     voz
    -0.68
    صلاح
    -0.68
    akukan
    -0.68
    POSITIVE LOGITS
     Potato
    0.91
    rousel
    0.83
     nombreux
    0.82
    емые
    0.78
     potato
    0.77
     Archa
    0.75
     hinzugefügt
    0.75
    ceiro
    0.75
     insinu
    0.75
    ège
    0.75
    Activations Density 0.033%

    No Known Activations