© 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. 32085
    Prev
    Next
    INDEX
    Explanations

    methyl, dimethyl, propyl groups

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

    chemical compound names and molecular structures, particularly those containing methyl and ammonium groups.

    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
     Acton
    -0.81
     HES
    -0.76
    зки
    -0.73
    젯
    -0.73
    ねー
    -0.72
     Mers
    -0.72
    adjective
    -0.72
     typewriter
    -0.71
    贷款
    -0.71
    Through
    -0.70
    POSITIVE LOGITS
     Produktions
    0.92
    חד
    0.81
    araman
    0.78
    olarmente
    0.77
    homem
    0.76
    tability
    0.76
     dì
    0.75
     halv
    0.75
     Москов
    0.74
     Sloveniji
    0.74
    Activations Density 0.088%

    No Known Activations