© 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. 58939
    Prev
    Next
    INDEX
    Explanations

    corporate, Charities, registries

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

    The neuron primarily recognizes and activates on numeric tokens (digits, numeric codes, counts, and other number sequences) 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
     ము
    -0.69
     μπα
    -0.69
    Britt
    -0.69
    一同
    -0.69
     waitFor
    -0.69
     invader
    -0.68
    mpo
    -0.68
     kiin
    -0.67
    èm
    -0.67
    änk
    -0.66
    POSITIVE LOGITS
     Registrar
    2.02
     registry
    1.88
     registrar
    1.77
     Companies
    1.76
    Registrar
    1.74
     Registry
    1.66
    registry
    1.55
     register
    1.49
    Registry
    1.48
     regist
    1.48
    Activations Density 0.015%

    No Known Activations