© 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. 34-GEMMASCOPE-RES-131K
    7. 30935
    Prev
    Next
    INDEX
    Explanations

    black holes

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

    The neuron strongly activates on digits, mathematical symbols (e.g. parentheses, hyphens) and other notation tokens common in technical or scientific/mathematical contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     слуша
    -0.76
    踝
    -0.73
     Betis
    -0.73
    뿜
    -0.73
    netty
    -0.72
     autora
    -0.72
    melis
    -0.69
     作者
    -0.68
    ższych
    -0.68
     Gebäude
    -0.68
    POSITIVE LOGITS
     bran
    1.34
    bran
    1.13
     D
    1.09
     Dp
    0.88
     Bran
    0.82
     intersecting
    0.81
    סת
    0.79
     Brennan
    0.79
     plowed
    0.77
    Dp
    0.76
    Activations Density 0.042%

    No Known Activations