© 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. 68150
    Prev
    Next
    INDEX
    Explanations

    conjunctions and abbreviations

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

    This neuron detects parenthetical “also known as/romanized as” name‐variant phrases.

    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
    ◉
    -0.97
    ־ה
    -0.94
     paie
    -0.94
    ГЛА
    -0.93
     baratas
    -0.90
    作詞
    -0.90
    糠
    -0.90
    gerea
    -0.89
     rechange
    -0.88
    に於
    -0.88
    POSITIVE LOGITS
     and
    3.41
    性和
    1.07
     NY
    0.99
     и
    0.94
     or
    0.93
     και
    0.92
     AND
    0.91
    vi
    0.90
    および
    0.89
     OR
    0.88
    Activations Density 0.052%

    No Known Activations