© 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. 25735
    Prev
    Next
    INDEX
    Explanations

    Eastern Cape

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

    This neuron responds to numeric tokens, i.e. it detects numbers or numerical quantities in the text.

    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
    pss
    -0.96
     mitään
    -0.94
     celebridades
    -0.93
     esconder
    -0.90
     abstrato
    -0.88
     prohibido
    -0.85
     asesinado
    -0.85
     embreagem
    -0.84
     relevantes
    -0.82
     embrague
    -0.82
    POSITIVE LOGITS
     target
    1.00
    if
    0.91
    xase
    0.90
     you
    0.89
     يول
    0.89
    rata
    0.88
    target
    0.85
    COR
    0.85
    NAME
    0.84
     each
    0.84
    Activations Density 0.010%

    No Known Activations