© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43767
    Prev
    Next
    INDEX
    Explanations

    first, most, winner

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

    This neuron detects ranking and ordering expressions, especially ordinals and superlatives (e.g. “first,” “one of the,” “most,” “leading”).

    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
     (
    -1.12
     pogod
    -1.04
     chimique
    -1.02
    (
    -1.02
     I
    -1.00
     usual
    -1.00
     would
    -0.99
     also
    -0.97
     details
    -0.95
     électron
    -0.94
    POSITIVE LOGITS
     because
    1.80
     by
    1.55
     of
    1.44
    Dimanche
    1.36
     until
    1.30
    Lundi
    1.22
     bahkan
    1.20
    because
    1.16
     çünkü
    1.16
     sınır
    1.13
    Activations Density 0.144%

    No Known Activations