© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22321
    Prev
    Next
    INDEX
    Explanations

    adverse events or conditions

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

    phrases describing narrative situations or scenes, particularly involving characters in specific locations or circumstances.

    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
     является
    -1.84
     туры
    -1.62
     Öffnungszeiten
    -1.58
     årets
    -1.55
     عندما
    -1.52
    telah
    -1.49
     refusé
    -1.48
    åter
    -1.48
     expliqué
    -1.47
    camisas
    -1.46
    POSITIVE LOGITS
     these
    2.09
     we
    2.08
     our
    2.03
     more
    1.88
     it
    1.87
     acestea
    1.63
     noastră
    1.60
     These
    1.54
    <tr>
    1.52
     so
    1.48
    Activations Density 0.054%

    No Known Activations