© 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. 66794
    Prev
    Next
    INDEX
    Explanations

    additional, extra, second, another

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

    This neuron activates on words that signal enumeration or sequence (e.g., another, second, remaining, additional, more).

    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
    谗
    -1.00
    roxene
    -0.99
     néer
    -0.96
    skich
    -0.96
    當時
    -0.96
    怎麼辦
    -0.96
    готовление
    -0.93
    \[
    -0.93
    诧异
    -0.92
    というわけで
    -0.91
    POSITIVE LOGITS
     wipers
    0.86
     nigga
    0.81
     height
    0.79
    Manufactured
    0.79
    ことにしました
    0.78
     dupa
    0.78
    WRITER
    0.78
     immaculate
    0.77
    =-=-=-=-
    0.77
     ویکی‌پدیای
    0.76
    Activations Density 0.022%

    No Known Activations