© 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. 103499
    Prev
    Next
    INDEX
    Explanations

    only want

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

    This neuron fires on the qualifying adverb “only,” marking statements that limit or qualify an amount or action.

    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
     chỉ
    -1.71
    ↵↵
    -1.64
     zeichnet
    -1.49
    ዣ
    -1.44
     felicitación
    -1.44
    戆
    -1.43
    (
    -1.43
    他の
    -1.43
     bezeichnet
    -1.42
     Placing
    -1.40
    POSITIVE LOGITS
     maniere
    1.63
     suscit
    1.41
    lands
    1.35
    荅
    1.31
     pecuni
    1.31
    álbum
    1.30
     sociali
    1.30
     But
    1.29
    Adapun
    1.29
     todav
    1.26
    Activations Density 0.016%

    No Known Activations