© 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. 10-GEMMASCOPE-RES-131K
    7. 112630
    Prev
    Next
    INDEX
    Explanations

    forms of writing

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

    The neuron detects mentions of the act of writing—especially past‐tense and related forms like “wrote,” “written,” and “writing.”

    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
    蛩
    -1.37
     furt
    -1.28
    hance
    -1.25
    Mutagenicity
    -1.23
     Meski
    -1.23
    ޅ
    -1.23
    👯
    -1.21
    -..
    -1.20
    OGLE
    -1.20
     benzin
    -1.17
    POSITIVE LOGITS
    ↵
    1.27
     <
    1.23
     in
    1.23
    i
    1.23
     escrito
    1.18
    ;
    1.12
     =
    1.09
    jenigen
    1.09
    ).
    1.09
    :
    1.09
    Activations Density 0.105%

    No Known Activations