© 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. 34-GEMMASCOPE-RES-131K
    7. 116998
    Prev
    Next
    INDEX
    Explanations

    knows someone personally

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

    The neuron strongly activates on occurrences of the verb “know” (and its inflected forms).

    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
    ərbay
    -0.87
    ANCO
    -0.81
    Ellips
    -0.78
     itself
    -0.77
    ドーム
    -0.77
     bonito
    -0.73
    abend
    -0.72
     בנו
    -0.72
    乖乖
    -0.72
    プリ
    -0.71
    POSITIVE LOGITS
     personally
    2.09
     intimately
    1.66
     well
    1.48
     személy
    1.34
     лично
    1.31
     persönlich
    1.24
    Personally
    1.20
     Personally
    1.20
     from
    1.19
     personal
    1.15
    Activations Density 0.020%

    No Known Activations