© 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. 63873
    Prev
    Next
    INDEX
    Explanations

    mentioning personal recipes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    美味しそう
    -1.23
     pastries
    -1.14
    曲は
    -1.10
    キャベツ
    -1.09
     coffee
    -1.08
     donuts
    -1.07
     champagne
    -1.07
    玉ねぎ
    -1.03
     ejemplos
    -1.02
    味は
    -1.01
    POSITIVE LOGITS
     recipe
    1.76
     served
    1.20
     making
    1.18
     Recipe
    1.17
     adapted
    1.13
    recipe
    1.13
    Adapted
    1.09
     recipes
    1.07
     만들
    1.07
    Texture
    1.03
    Activations Density 0.091%

    No Known Activations