© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84780
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    The neuron does not activate on any of the shown tokens—it doesn’t consistently pick out any particular pattern.

    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
     to
    -2.53
    ’
    -2.42
     for
    -2.05
    “
    -1.68
    .”
    -1.68
     '../../../../
    -1.67
     if
    -1.66
     because
    -1.65
    mathrm
    -1.62
    と思ったら
    -1.62
    POSITIVE LOGITS
    🕗
    2.17
    Beskrivning
    2.05
    Beskrivelse
    1.91
    Zubereitung
    1.87
    Wady
    1.77
    Groet
    1.72
    人是
    1.64
    晙
    1.59
    ştır
    1.59
    瑧
    1.56
    Activations Density 0.015%

    No Known Activations