© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63305
    Prev
    Next
    INDEX
    Explanations

    possessives and contractions

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

    The neuron strongly responds to tokens that are punctuation marks (especially apostrophes/quotes) or numeric characters.

    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
    aglio
    -0.84
     usia
    -0.78
    图为
    -0.75
    lees
    -0.74
    getSubject
    -0.74
    绮
    -0.73
     wire
    -0.73
     heterogeneous
    -0.73
     Grig
    -0.72
    睿
    -0.71
    POSITIVE LOGITS
    アメリカ
    0.85
    Sistema
    0.84
    via
    0.81
     /^[
    0.81
     Durban
    0.81
    これは
    0.79
     secre
    0.76
     redacción
    0.76
     cincin
    0.75
    PRNewswire
    0.75
    Activations Density 0.011%

    No Known Activations