© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92128
    Prev
    Next
    INDEX
    Explanations

    rights reserved

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

    The neuron fires on numeric tokens, especially multi‐digit numbers such as years or large numeric constants.

    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
     Phipps
    -0.84
     dites
    -0.76
    larınız
    -0.75
    rowski
    -0.75
    друг
    -0.75
     varias
    -0.74
     שנה
    -0.73
     sot
    -0.72
    ledad
    -0.71
    薪
    -0.69
    POSITIVE LOGITS
    bleshooting
    0.88
    ̗
    0.81
    addis
    0.76
    monsters
    0.75
    oforte
    0.74
    umar
    0.73
    XtraGrid
    0.73
    ="">
    0.73
    objectives
    0.72
    architecte
    0.72
    Activations Density 0.362%

    No Known Activations