© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 69934
    Prev
    Next
    INDEX
    Explanations

    baking ingredients and reactions

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

    chemical compounds, ingredients, and scientific formulas in cooking recipes or technical documents.

    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
    glue
    -0.78
    daos
    -0.76
    gulan
    -0.75
    orky
    -0.73
    claration
    -0.68
     baseline
    -0.67
    famous
    -0.66
    ∛
    -0.65
     reimbursement
    -0.65
    guila
    -0.64
    POSITIVE LOGITS
     baking
    1.73
     Baking
    1.61
     chemical
    1.34
    Baking
    1.27
     soda
    1.19
    chemical
    1.14
    baking
    1.14
     Chemical
    1.13
     reaction
    1.13
     Reaction
    1.06
    Activations Density 0.008%

    No Known Activations