© 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. 118008
    Prev
    Next
    INDEX
    Explanations

    the company

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

    The neuron fires on standalone numeric tokens (especially multi-digit numbers such as years, quantities, prices, or other numeric data).

    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
    𝑁
    -0.79
    idelberg
    -0.77
     měli
    -0.77
     conectados
    -0.74
    здание
    -0.74
    shima
    -0.74
    Xk
    -0.73
    )\}$
    -0.73
    ôs
    -0.73
    źnie
    -0.72
    POSITIVE LOGITS
     company
    8.50
    company
    6.13
     Company
    5.78
    Company
    5.69
    公司
    5.16
     COMPANY
    4.72
    COMPANY
    4.63
     компании
    4.41
     compañía
    4.31
     empresa
    4.25
    Activations Density 0.175%

    No Known Activations