© 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. 9903
    Prev
    Next
    INDEX
    Explanations

    names of meals

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

    The neuron responds strongly to words naming meals or mealtimes (e.g. breakfast, lunch, dinner).

    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
     to
    -2.39
    '])->
    -1.59
    -“
    -1.45
    ⛤
    -1.45
    =>"
    -1.43
    (“
    -1.39
    `(
    -1.36
    робі
    -1.36
     econômica
    -1.34
    🧌
    -1.33
    POSITIVE LOGITS
     ''
    1.64
     =
    1.56
    .....
    1.48
    The
    1.41
     »
    1.39
    Hrsg
    1.39
        
    1.36
    Ông
    1.35
     )
    1.34
    をする
    1.34
    Activations Density 0.012%

    No Known Activations