© 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. 34-GEMMASCOPE-RES-131K
    7. 77463
    Prev
    Next
    INDEX
    Explanations

    in many ways/respects

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

    The neuron detects quantifier or enumeration words and phrases (e.g. “many,” “all,” “some,” “in several ways”) that signal listing or multiple items.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    baju
    -1.05
    ட்டி
    -0.80
    КС
    -0.80
    ӹ
    -0.78
    levering
    -0.77
    ณ
    -0.75
    ówek
    -0.75
    äf
    -0.75
    利用
    -0.74
    щению
    -0.73
    POSITIVE LOGITS
     respects
    4.44
     respect
    3.86
     ways
    2.95
    respect
    2.92
    Respect
    2.75
     regards
    2.69
     Respect
    2.64
     regard
    2.59
     respecto
    2.38
     RESPECT
    2.27
    Activations Density 0.034%

    No Known Activations