© 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. 8598
    Prev
    Next
    INDEX
    Explanations

    asking for help or advice

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

    This neuron fires on question-leading auxiliary verbs (e.g. “Does,” “Can,” “Is”) at the start of an inquiry.

    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
    ouest
    -0.89
    незон
    -0.88
    他也
    -0.85
    asList
    -0.84
     которых
    -0.84
    endid
    -0.83
    toj
    -0.82
     ANOTHER
    -0.81
    coa
    -0.81
     milhões
    -0.80
    POSITIVE LOGITS
     anyone
    3.84
     anybody
    2.84
    anyone
    2.45
    Anyone
    2.39
     someone
    1.91
     Anyone
    1.86
    Anybody
    1.74
     any
    1.73
     Anybody
    1.66
     کسی
    1.62
    Activations Density 0.093%

    No Known Activations