© 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. 106948
    Prev
    Next
    INDEX
    Explanations

    citrus, zest, peel, juice

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

    ingredients and measurements in recipes or cooking instructions.

    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
    唏
    -0.75
     =-
    -0.75
    лте
    -0.75
     socials
    -0.75
     sicurezza
    -0.73
    leet
    -0.72
    ennent
    -0.69
    staw
    -0.69
     voyant
    -0.69
    lceil
    -0.69
    POSITIVE LOGITS
     zest
    1.86
     peel
    1.13
     z
    1.08
     Z
    1.06
     orange
    0.99
     lemon
    0.90
     kulit
    0.89
    ピール
    0.85
     citrus
    0.83
    peel
    0.82
    Activations Density 0.018%

    No Known Activations