© 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. 34-GEMMASCOPE-RES-131K
    7. 58309
    Prev
    Next
    INDEX
    Explanations

    suspected exposure or contact

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

    text related to disease exposure, infection, and transmission between individuals.

    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
    lire
    -0.75
    भु
    -0.75
     olie
    -0.74
    接続
    -0.73
    Complaints
    -0.73
    THC
    -0.72
     impri
    -0.71
    hez
    -0.71
     antiche
    -0.71
     flotte
    -0.70
    POSITIVE LOGITS
     contacts
    1.49
     close
    1.39
     contact
    1.31
     suspected
    1.20
     exposure
    1.18
    接觸
    1.15
    contacts
    1.12
     suspect
    1.09
     Close
    1.08
    close
    1.07
    Activations Density 0.008%

    No Known Activations