© 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. 10-GEMMASCOPE-RES-131K
    7. 118996
    Prev
    Next
    INDEX
    Explanations

    food ingredients and preparations

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

    food items in cooking or restaurant contexts, especially meat, fish, and prepared dishes.

    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_10/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
     内衣
    -1.77
    钍
    -1.60
    tigte
    -1.60
     inconce
    -1.58
     frivol
    -1.55
     apareceu
    -1.55
    ⑽
    -1.55
     intrigu
    -1.52
    attaque
    -1.48
     oub
    -1.47
    POSITIVE LOGITS
     "
    1.85
     as
    1.84
     at
    1.81
     still
    1.76
     of
    1.67
     et
    1.67
     one
    1.66
     on
    1.66
     c
    1.64
     all
    1.60
    Activations Density 0.011%

    No Known Activations