© 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. 92211
    Prev
    Next
    INDEX
    Explanations

    saying or claiming

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

    The neuron fires most strongly on content-bearing, topic-specific words (i.e. keywords rather than common function words).

    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
     उसने
    -1.66
    它們
    -1.16
    它们
    -1.00
     їх
    -0.99
     ones
    -0.98
    它们的
    -0.96
    шает
    -0.95
     می‌تواند
    -0.93
    Them
    -0.93
    φέρει
    -0.92
    POSITIVE LOGITS
     have
    1.95
     they
    1.81
     say
    1.69
     κάν
    1.63
     themselves
    1.62
    вают
    1.52
     argue
    1.38
     कहते
    1.33
     claim
    1.32
    say
    1.32
    Activations Density 0.051%

    No Known Activations