© 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. 60790
    Prev
    Next
    INDEX
    Explanations

    drawing commands and specific entities

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

    The neuron is triggered by unusually long contiguous tokens (e.g. multi-letter function or class names and long words) in the text.

    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
    n
    -2.92
    ’
    -2.89
    as
    -2.83
    d
    -2.69
    v
    -2.50
    ve
    -2.48
    ви
    -2.48
    ed
    -2.48
    l
    -2.48
    <em>
    -2.47
    POSITIVE LOGITS
    ﮑ
    2.94
    ︓
    2.77
    鬭
    2.69
    眥
    2.64
    騭
    2.61
     colocando
    2.58
    ᡴ
    2.58
    März
    2.48
     burbu
    2.48
     desmotiv
    2.47
    Activations Density 0.000%

    No Known Activations