© 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. 22-GEMMASCOPE-RES-131K
    7. 25471
    Prev
    Next
    INDEX
    Explanations

    article or preposition followed by noun

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

    This neuron responds to words that denote measurements or magnitudes (e.g. “length,” “greater”).

    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
    の為
    -2.08
    ༷
    -2.06
     réellement
    -2.06
    の商品
    -2.03
    為に
    -2.02
     oído
    -2.02
    の方に
    -2.00
    泐
    -2.00
     páns
    -2.00
     longues
    -2.00
    POSITIVE LOGITS
     in
    2.78
     as
    2.50
     during
    2.38
     for
    2.27
     after
    2.25
     when
    2.20
     despite
    2.19
     at
    2.14
     without
    2.13
     since
    2.13
    Activations Density 0.026%

    No Known Activations