© 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. 10-GEMMASCOPE-RES-131K
    7. 128169
    Prev
    Next
    INDEX
    Explanations

    paraphrase what

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

    This neuron detects discourse cues where the author signals personal commentary or stance—words like “agree,” “with,” “like,” “paraphrase,” or “quote” that introduce opinion or agreement.

    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
    Yeni
    -1.68
     versátil
    -1.49
     sólida
    -1.48
    푠
    -1.48
     líquido
    -1.47
     sólido
    -1.45
     refrigerador
    -1.45
    會議
    -1.42
    代の
    -1.42
    ynchronously
    -1.42
    POSITIVE LOGITS
     with
    1.75
    w
    1.50
    b
    1.48
    y
    1.45
    v
    1.41
    [
    1.39
     follows
    1.38
    f
    1.37
     was
    1.34
     hará
    1.34
    Activations Density 0.036%

    No Known Activations