© 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. 63718
    Prev
    Next
    INDEX
    Explanations

    pepper and peppery

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

    The neuron fires on mentions of pepper or related spice/seasoning terms (e.g., “pepper,” “black pepper,” “piperine,” “salt,” “soy sauce” measurements in recipes).

    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
     practices
    -0.77
    practices
    -0.77
     Moj
    -0.74
    Purple
    -0.72
    practice
    -0.72
     Palette
    -0.71
     fridge
    -0.69
    piles
    -0.69
     chứa
    -0.69
     PRACTICES
    -0.68
    POSITIVE LOGITS
     pepper
    2.08
     Pepper
    1.63
    pepper
    1.59
    Pepper
    1.38
    胡椒
    1.28
     Piper
    1.15
     poivre
    1.09
     black
    1.06
     PEP
    1.05
     pimienta
    1.02
    Activations Density 0.015%

    No Known Activations