© 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. 434
    Prev
    Next
    INDEX
    Explanations

    overview, total, overall, general

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

    The neuron strongly activates on numeric tokens (three‐digit numbers) and on Chinese characters or their romanized surnames.

    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
    uric
    -0.79
    madol
    -0.78
    lifer
    -0.77
     including
    -0.77
    izers
    -0.77
    currentPlayer
    -0.74
     straightening
    -0.70
     että
    -0.70
    Pinterest
    -0.70
    <0xA3>
    -0.69
    POSITIVE LOGITS
     raccol
    0.86
    Gesam
    0.77
     phải
    0.76
    Overview
    0.75
    tagext
    0.74
    leitungen
    0.74
     Seu
    0.73
    Tổng
    0.73
     overview
    0.73
    leitung
    0.72
    Activations Density 0.011%

    No Known Activations