© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 119377
    Prev
    Next
    INDEX
    Explanations

    Converse shoes

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

    This neuron activates on tokens that are part of shoe brand or model names.

    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
     código
    -0.80
     nightclub
    -0.75
     Vaj
    -0.73
    landse
    -0.73
    Discounts
    -0.72
     makam
    -0.72
    шой
    -0.72
    ponenten
    -0.72
    cepatan
    -0.71
    OutputPath
    -0.71
    POSITIVE LOGITS
     canvas
    1.38
     Converse
    1.29
    canvas
    1.20
     vulcan
    1.16
     Chuck
    1.16
    Canvas
    1.13
    Chuck
    1.09
    Converse
    1.02
     low
    1.02
     Low
    1.01
    Activations Density 0.012%

    No Known Activations