© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67943
    Prev
    Next
    INDEX
    Explanations

    court filings and dates

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

    This neuron is triggered by long runs of leading whitespace (indented or blank-space sections).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    D
    -2.19
    P
    -1.95
    m
    -1.93
    G
    -1.89
    t
    -1.88
    F
    -1.88
    B
    -1.84
    K
    -1.84
    U
    -1.84
    N
    -1.82
    POSITIVE LOGITS
     camiset
    1.78
     granat
    1.74
    ᯾
    1.73
     extré
    1.67
     brisa
    1.64
     dekol
    1.63
     intelek
    1.61
    蕺
    1.60
     kreat
    1.60
     frança
    1.57
    Activations Density 0.012%

    No Known Activations