© 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. 34-GEMMASCOPE-RES-131K
    7. 93346
    Prev
    Next
    INDEX
    Explanations

    breakfast cereals and grains

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

    The neuron strongly fires on specific food product or brand names (especially cereals and their makers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     ACO
    -0.81
     Psalm
    -0.78
     NLP
    -0.78
     carrots
    -0.75
    гию
    -0.75
    ลิ
    -0.74
     Oktober
    -0.71
    婪
    -0.70
    ────────
    -0.70
    Jess
    -0.69
    POSITIVE LOGITS
     cereal
    2.66
     cereals
    2.06
     Cereal
    2.02
     Kellogg
    1.67
    cere
    1.59
    🥣
    1.54
     breakfast
    1.43
     flakes
    1.30
     Cheer
    1.29
     céré
    1.22
    Activations Density 0.010%

    No Known Activations