© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67869
    Prev
    Next
    INDEX
    Explanations

    instructions and beginnings

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

    This neuron fires on numeric ingredient‐quantity tokens (the numbers in recipe ingredient lists).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ætter
    -1.04
     those
    -0.98
     />,
    -0.96
     }).
    -0.95
     сказки
    -0.95
    ølge
    -0.94
     one
    -0.94
    ),),
    -0.92
    sims
    -0.90
     there
    -0.89
    POSITIVE LOGITS
    Zubereitung
    1.02
     minore
    0.96
     aucune
    0.96
    ଼
    0.95
     ابتدا
    0.92
    首先
    0.92
     Menurut
    0.91
     numéros
    0.91
     procedimiento
    0.90
     procedimento
    0.90
    Activations Density 0.016%

    No Known Activations