© 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. 22-GEMMASCOPE-RES-131K
    7. 71781
    Prev
    Next
    INDEX
    Explanations

    existence, there, we

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

    The neuron fires strongly on reference‐style markers and annotations—asterisks, brackets or quotation symbols used as footnotes or section dividers, and inline numeric citations.

    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
     or
    -1.90
     and
    -1.84
     which
    -1.66
     on
    -1.37
    itação
    -1.35
     причем
    -1.34
     framför
    -1.32
    titure
    -1.32
     with
    -1.32
     an
    -1.32
    POSITIVE LOGITS
     it
    3.81
     there
    3.50
     we
    3.03
     they
    2.97
     you
    2.36
     هناك
    1.71
    despite
    1.64
    盌
    1.63
     nobody
    1.57
    THERE
    1.54
    Activations Density 0.027%

    No Known Activations