© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83778
    Prev
    Next
    INDEX
    Explanations

    Stripe, plotly, Drake, обла

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

    The neuron fires on occurrences of the substring “stripe” (e.g. “Stripe,” “stripe,” “stripes,” “pin‐stripe,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    s
    -2.47
    _
    -2.34
    h
    -2.31
    ro
    -2.28
    often
    -2.27
    —-
    -2.23
    ים
    -2.17
    ल
    -2.17
    ’).
    -2.17
     mediocre
    -2.14
    POSITIVE LOGITS
    hamilan
    1.98
    鱨
    1.94
    鳧
    1.91
    ありません
    1.88
    penas
    1.75
    摇了
    1.74
    which
    1.73
    黽
    1.72
    umán
    1.72
     और
    1.70
    Activations Density 0.001%

    No Known Activations