© 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. 22-GEMMASCOPE-RES-131K
    7. 35729
    Prev
    Next
    INDEX
    Explanations

    saying it is the way

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

    The neuron strongly responds to first-person statements expressing personal interest in video games.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ଶ
    -1.34
    makeatother
    -1.27
     now
    -1.24
    #@
    -1.23
    érables
    -1.23
     nochmals
    -1.23
     heretofore
    -1.22
    #
    -1.20
     will
    -1.19
    &)
    -1.18
    POSITIVE LOGITS
     kinda
    1.50
     things
    1.49
     kind
    1.46
     بشكل
    1.41
     probablemente
    1.38
     debido
    1.36
     they
    1.33
     tamamen
    1.32
     específicamente
    1.32
     people
    1.28
    Activations Density 0.019%

    No Known Activations