© 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. 77761
    Prev
    Next
    INDEX
    Explanations

    thio followed by chemical endings

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

    chemical compounds with "thio" prefix, particularly in scientific/medical 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_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
    entos
    -0.75
    lassification
    -0.75
     cruzar
    -0.73
    chauffer
    -0.73
     mixes
    -0.73
    𐌸
    -0.71
    の結果
    -0.71
    hollywood
    -0.71
     markiert
    -0.70
    umerate
    -0.69
    POSITIVE LOGITS
    zett
    0.84
     the
    0.82
     Jeep
    0.80
     earthen
    0.79
     رون
    0.75
    other
    0.75
    釦
    0.75
    yre
    0.73
     wsz
    0.73
     Auction
    0.71
    Activations Density 0.003%

    No Known Activations