© 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. 10-GEMMASCOPE-RES-131K
    7. 14439
    Prev
    Next
    INDEX
    Explanations

    food items, medicine, and calendar events

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

    food items and kitchen-related terms.

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

    The neuron fires on concrete noun tokens naming tangible objects, products, or items.

    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
    atical
    -1.21
     食事
    -1.18
     only
    -1.18
    piles
    -1.16
     estuviera
    -1.16
    rageous
    -1.13
    ;%%
    -1.13
    sprodu
    -1.13
    atever
    -1.11
    ⡯
    -1.09
    POSITIVE LOGITS
     here
    1.44
     how
    1.42
     will
    1.33
    meldet
    1.30
     what
    1.28
     like
    1.13
     ہیں
    1.13
    줬
    1.13
     relaciona
    1.13
    ={[
    1.10
    Activations Density 0.097%

    No Known Activations