© 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. 10-GEMMASCOPE-RES-131K
    7. 74965
    Prev
    Next
    INDEX
    Explanations

    stakes, Genius, ICAREUM

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

    The neuron fires on multi‐digit numeric tokens—especially monetary amounts or other large numbers, often with commas and zeros.

    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
     now
    -1.87
     этой
    -1.84
     conseillé
    -1.82
    泐
    -1.79
     kwamba
    -1.75
     accompagné
    -1.73
    ૉ
    -1.72
     you
    -1.70
    bảng
    -1.69
     parcourir
    -1.69
    POSITIVE LOGITS
     with
    2.00
     but
    2.00
     Before
    1.74
     With
    1.61
     in
    1.56
     While
    1.55
     During
    1.53
     including
    1.51
    ত্র
    1.46
     Without
    1.44
    Activations Density 0.007%

    No Known Activations