© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 47945
    Prev
    Next
    INDEX
    Explanations

    code elements or structure

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

    The neuron activates on numeric literals (integers or decimals) 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
    责任编辑
    -1.44
     brisa
    -1.43
    ⠛
    -1.40
     спасибо
    -1.38
     просто
    -1.33
    Recently
    -1.30
    Just
    -1.28
    呖
    -1.28
    Use
    -1.26
    To
    -1.25
    POSITIVE LOGITS
     from
    2.11
     when
    1.88
     until
    1.81
     along
    1.75
     since
    1.59
     except
    1.59
     and
    1.52
     because
    1.50
     keduanya
    1.44
     unless
    1.39
    Activations Density 0.058%

    No Known Activations