© 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. 42847
    Prev
    Next
    INDEX
    Explanations

    introducing conclusions or inferences

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

    The neuron is strongly activated by numeric expressions (e.g. integers, decimals, percentages) representing quantitative 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
     HIEROGLYPH
    -1.77
     three
    -1.63
     may
    -1.55
    🖤
    -1.53
    🙌
    -1.52
    😜
    -1.51
    😌
    -1.51
     CALIFORNI
    -1.49
     received
    -1.49
     seems
    -1.49
    POSITIVE LOGITS
    沵
    1.83
     souvent
    1.80
    髫
    1.79
     jiné
    1.66
     hebben
    1.59
    螃
    1.58
     maintenant
    1.58
     they
    1.56
     rô
    1.56
     parfois
    1.55
    Activations Density 0.031%

    No Known Activations