© 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. 40999
    Prev
    Next
    INDEX
    Explanations

    software documentation and licenses

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

    The neuron fires on the special indentation or leading‐whitespace tokens that mark the start of formatted blocks or section headings.

    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
     we
    -2.02
    [
    -1.93
    之类的
    -1.90
     lorsque
    -1.88
    来自于
    -1.80
     .
    -1.80
     它
    -1.78
    _'
    -1.73
    .'
    -1.73
    \\
    -1.70
    POSITIVE LOGITS
    榈
    2.28
    ípio
    2.22
    ización
    2.13
    óricas
    2.09
    ant
    2.08
    zieć
    2.08
    WriteLiteral
    2.05
    vantaged
    2.05
    ellees
    2.02
    ruly
    2.00
    Activations Density 0.004%

    No Known Activations