© 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. 34-GEMMASCOPE-RES-131K
    7. 34936
    Prev
    Next
    INDEX
    Explanations

    email suffixes or URLs

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

    This neuron responds to tokens that are part of structured identifiers or names—acronyms, parenthetical qualifiers, file‐path or namespace separators, and other uppercase-and-punctuation–laden 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_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
    举报
    -0.81
     burdened
    -0.78
     allotment
    -0.73
    anganese
    -0.73
    之路
    -0.73
    ͳ
    -0.72
    ोग
    -0.70
     Trying
    -0.69
    ・・・・
    -0.69
     befes
    -0.69
    POSITIVE LOGITS
     bảo
    0.84
    ANTE
    0.83
    lija
    0.81
     zap
    0.80
     ?)
    0.78
    蝎
    0.77
    mā
    0.77
    Bec
    0.76
    パティ
    0.76
    Obi
    0.75
    Activations Density 1.198%

    No Known Activations