© 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. 10-GEMMASCOPE-RES-131K
    4. 60922
    Prev
    Next
    INDEX
    Explanations

    ABC followed by separators or variations

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

    This neuron detects the uppercase sequence “ABC” (as in TV network or channel identifiers).

    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
     Its
    -1.95
    '
    -1.94
     a
    -1.94
    {
    -1.80
     reduziert
    -1.73
     customize
    -1.67
     penelitian
    -1.66
     Она
    -1.65
     estableció
    -1.62
     spielte
    -1.58
    POSITIVE LOGITS
     estekak
    2.11
    atação
    1.95
    0
    1.95
    鬭
    1.84
     terremoto
    1.73
    ープン
    1.70
     撮っ
    1.67
    ጴ
    1.64
    Symb
    1.60
    Ꮔ
    1.60
    Activations Density 0.001%

    No Known Activations