© 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. 34-GEMMASCOPE-RES-131K
    4. 93806
    Prev
    Next
    INDEX
    Explanations

    Keloid, Kelley, Kelvingrove, Kelam, Kellogg

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

    This neuron activates on any occurrence of the character sequence “kel” (in any casing) within a word.

    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
    INSTR
    -0.75
     jerry
    -0.73
     Inten
    -0.71
    Interes
    -0.70
    EDM
    -0.70
     Perfectly
    -0.69
    RANDOM
    -0.68
     checkup
    -0.68
    があります
    -0.66
    injection
    -0.66
    POSITIVE LOGITS
    her
    0.90
    合理
    0.90
     Kel
    0.86
    Kel
    0.80
     kel
    0.79
    so
    0.79
    words
    0.77
    ဦ
    0.77
    haltens
    0.76
    probability
    0.75
    Activations Density 0.011%

    No Known Activations