© 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. 11965
    Prev
    Next
    INDEX
    Explanations

    food preferences and textures

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

    discussions about food preferences, eating habits, or culinary experiences.

    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
    美味し
    -1.10
    values
    -0.99
     muffins
    -0.98
    豚肉
    -0.98
    キャベツ
    -0.98
     delicioso
    -0.97
     croissants
    -0.94
     membunuh
    -0.93
    hmig
    -0.90
     サンダル
    -0.89
    POSITIVE LOGITS
     liking
    1.34
     texture
    1.34
     adventurous
    1.22
     textures
    1.14
     picky
    1.12
     Texture
    1.11
     preferences
    1.08
     dislike
    1.07
     preferring
    1.05
     tolerate
    1.05
    Activations Density 0.033%

    No Known Activations