© 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. 54186
    Prev
    Next
    INDEX
    Explanations

    In proper nouns or fields

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

    The neuron detects the leading tokens of an article’s opening line (e.g. the subject name or initial “In …” phrase at the start of each entry).

    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
    なんだろう
    -1.08
     الشيخ
    -1.07
     regular
    -0.95
     standard
    -0.93
     everyone
    -0.91
     आया
    -0.90
    なんだけど
    -0.90
    なのだ
    -0.90
    感激
    -0.89
     random
    -0.88
    POSITIVE LOGITS
     Coordin
    1.04
    】：
    0.88
     Cornelia
    0.88
    为
    0.87
    nienie
    0.86
     EIR
    0.86
    类的
    0.85
    눙
    0.85
     💯
    0.85
     Differenti
    0.84
    Activations Density 0.022%

    No Known Activations