© 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. 107602
    Prev
    Next
    INDEX
    Explanations

    generated numbers and symbols

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

    The neuron is primarily detecting numeric tokens (digits and numeric expressions).

    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
     Zinn
    -0.72
    ÷
    -0.70
    tapp
    -0.67
    wars
    -0.67
    vény
    -0.66
    TAM
    -0.66
    idać
    -0.66
    蕾
    -0.66
    ksam
    -0.65
     vang
    -0.65
    POSITIVE LOGITS
    cable
    0.86
    Cable
    0.81
     cords
    0.81
     cables
    0.79
     Mele
    0.79
     PARTE
    0.79
     cable
    0.78
    Origem
    0.77
     convirtió
    0.77
     cabling
    0.76
    Activations Density 0.005%

    No Known Activations