© 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. 20895
    Prev
    Next
    INDEX
    Explanations

    mathematical lines and technical terms

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

    The neuron fires on standalone punctuation tokens (not words), especially underscores and hyphens used as list or section separators.

    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
    and
    -2.44
    0
    -2.39
    on
    -2.38
    ↵↵
    -1.99
    ut
    -1.92
    for
    -1.84
    t
    -1.83
    y
    -1.80
     our
    -1.79
     impacting
    -1.73
    POSITIVE LOGITS
    ização
    2.22
    เกง
    2.19
    ícias
    2.16
     kalender
    2.13
    鲮
    2.05
    ilidade
    2.02
    asties
    1.98
    闥
    1.98
     indisponible
    1.98
     priser
    1.97
    Activations Density 0.002%

    No Known Activations