© 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. 10-GEMMASCOPE-RES-131K
    7. 70360
    Prev
    Next
    INDEX
    Explanations

    not one

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

    The neuron activates on occurrences of the quantifier “one” (and its close variant “single”) in text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    鸰
    -1.70
     \\
    -1.65
     perhaps
    -1.58
    DatabaseError
    -1.56
     possibly
    -1.56
    čka
    -1.55
     bolster
    -1.54
    Maybe
    -1.52
    僕
    -1.52
    說道
    -1.51
    POSITIVE LOGITS
     of
    2.78
     abd
    1.63
    ,
    1.52
    כת
    1.52
     drap
    1.51
    tiple
    1.48
     famili
    1.48
     erhi
    1.48
    cluding
    1.45
    怱
    1.45
    Activations Density 0.006%

    No Known Activations