© 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. 75516
    Prev
    Next
    INDEX
    Explanations

    diet manipulation and counseling

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

    The neuron detects the word "diet" and related nutritional terminology.

    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
    鵟
    -2.58
    綃
    -2.44
    ’;
    -2.44
    .
    -2.41
    .’
    -2.38
     –
    -2.34
    棪
    -2.33
     Многие
    -2.30
    鳧
    -2.30
    のご紹介
    -2.27
    POSITIVE LOGITS
     фильме
    2.78
    ſelves
    2.67
    }
    2.58
     destruir
    2.50
    ۸
    2.42
    是非常
    2.39
     години
    2.38
     cuando
    2.34
     preguntó
    2.33
    .
    2.33
    Activations Density 0.011%

    No Known Activations