© 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. 11743
    Prev
    Next
    INDEX
    Explanations

    protein nutrition and health

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

    The neuron activates for the word "protein" and related nutritional terms.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects occurrences of the word “protein” (and its plural form), especially when it appears in nutritional contexts with amounts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     it
    -2.45
     This
    -2.34
    5
    -2.20
    1
    -2.13
    (
    -2.11
    9
    -2.00
     Now
    -1.82
    噠
    -1.79
     Quickly
    -1.76
     Diese
    -1.75
    POSITIVE LOGITS
    𓋼
    2.11
    }$
    1.88
    婓
    1.86
     إذا
    1.84
    </sup>
    1.84
     untuk
    1.83
    驁
    1.80
     iedere
    1.79
    бѣ
    1.77
    炱
    1.77
    Activations Density 0.020%

    No Known Activations