© 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. 57364
    Prev
    Next
    INDEX
    Explanations

    participating nations

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

    This neuron fires on standalone, capitalized single-word headings or labels (e.g., section titles or parameter names) in the text.

    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
    orap
    -0.73
     code
    -0.69
     Horace
    -0.66
     Cister
    -0.63
    Ớ
    -0.63
     پایه
    -0.62
    奖
    -0.61
     Praise
    -0.61
     awak
    -0.61
    ᵧ
    -0.60
    POSITIVE LOGITS
     zult
    0.63
    ças
    0.62
    梦见
    0.62
    漯
    0.62
     olacak
    0.61
    ți
    0.61
     مصر
    0.61
    стасия
    0.61
     Chisholm
    0.60
     jorden
    0.60
    Activations Density 0.094%

    No Known Activations