© 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. 22-GEMMASCOPE-RES-131K
    7. 34462
    Prev
    Next
    INDEX
    Explanations

    conjunctions and particles

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

    The neuron is essentially inactive—it does not respond to any tokens.

    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
    は
    -2.17
     ;
    -2.05
    を
    -1.99
    が
    -1.84
     Alamofire
    -1.73
    
    -1.72
    [>
    -1.70
    歺
    -1.67
    ..(
    -1.66
    "
    -1.65
    POSITIVE LOGITS
     and
    2.78
     or
    1.95
    なのかな
    1.85
    のお話
    1.84
     belangrij
    1.80
    きち
    1.70
     啦
    1.69
    気がする
    1.66
    分から
    1.66
    無し
    1.65
    Activations Density 0.044%

    No Known Activations