© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41633
    Prev
    Next
    INDEX
    Explanations

    the [noun]

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

    The neuron activates on decimal or floating-point numerical measurements in the text.

    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
     recientes
    -1.55
    延伸閱讀
    -1.53
     recientemente
    -1.40
     manteniendo
    -1.40
     tampoco
    -1.37
    </strong>
    -1.34
     zudem
    -1.34
     защото
    -1.33
     reciente
    -1.33
     representado
    -1.32
    POSITIVE LOGITS
    通常
    1.63
     durer
    1.55
     Pakai
    1.48
    begin
    1.46
     vostre
    1.45
     tasche
    1.43
    燃料
    1.38
    j
    1.37
     Kampung
    1.36
     simpel
    1.36
    Activations Density 0.091%

    No Known Activations