© 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. 10-GEMMASCOPE-RES-131K
    7. 73972
    Prev
    Next
    INDEX
    Explanations

    study of

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

    academic research paper titles or introductions, particularly those containing "study of" phrases.

    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_10/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
     avancer
    -1.65
     créer
    -1.63
     bienvenue
    -1.59
    ਲ਼
    -1.59
    
    -1.55
     ziet
    -1.53
     tional
    -1.52
     normaal
    -1.52
     dépasser
    -1.49
     toont
    -1.49
    POSITIVE LOGITS
     for
    1.70
    Some
    1.61
     From
    1.59
     not
    1.58
     Almost
    1.55
     in
    1.52
    This
    1.45
     two
    1.43
     less
    1.41
     примерно
    1.41
    Activations Density 0.144%

    No Known Activations