© 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. 129038
    Prev
    Next
    INDEX
    Explanations

    search, the, each, simply, wrap, all

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

    The neuron fires on the opening or lead sentences that introduce and summarize a product or service offering.

    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
     to
    -2.02
     then
    -1.84
    _
    -1.59
     “
    -1.46
     bancaria
    -1.42
    そういえば
    -1.40
    さまざまな
    -1.37
     cewek
    -1.31
    どうやら
    -1.31
    おはよう
    -1.30
    POSITIVE LOGITS
     trabajado
    1.49
     nuestras
    1.49
     and
    1.48
     нам
    1.48
     duradero
    1.47
    .*;
    1.47
     sizi
    1.47
    Bains
    1.43
    Opere
    1.43
     mejora
    1.43
    Activations Density 0.071%

    No Known Activations