© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129992
    Prev
    Next
    INDEX
    Explanations

    build system paths and names

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

    The neuron activates on numeric literals (integer or floating‐point numbers) in code.

    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
    
    -2.58
    ⬈
    -2.55
    の為
    -2.38
    以外にも
    -2.23
    ！）
    -2.22
    をはじめ
    -2.14
    自体は
    -2.09
     aprendiz
    -2.03
     regiões
    -2.03
    bolsa
    -1.98
    POSITIVE LOGITS
    {
    2.53
    …’
    2.47
     —
    2.28
    et
    2.25
    <
    2.13
    are
    2.05
    .’
    2.05
    r
    2.03
    a
    2.03
    st
    2.03
    Activations Density 0.012%

    No Known Activations