© 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. 31930
    Prev
    Next
    INDEX
    Explanations

    chlorophenyl, chlorohydrin, chloramphenicol

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

    chemical compounds containing "chloro" prefixes or elements.

    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
     nitric
    -0.89
     linguistic
    -0.86
    criminator
    -0.79
     /*
    -0.77
    zonych
    -0.76
    nard
    -0.75
     clinics
    -0.75
     три
    -0.74
    cké
    -0.73
     blockchain
    -0.73
    POSITIVE LOGITS
     많은
    0.82
    idth
    0.80
    وصلات
    0.76
    GLI
    0.75
    ToSend
    0.75
    תּ
    0.73
    واقع
    0.73
    жника
    0.73
     ovviamente
    0.73
     zuhause
    0.73
    Activations Density 0.037%

    No Known Activations