© 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. 119289
    Prev
    Next
    INDEX
    Explanations

    mathematical questions with letter answers

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

    The neuron activates specifically on question‐mark tokens (i.e. the “?” indicating a question).

    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
     without
    -1.06
     if
    -1.03
     still
    -1.01
    ၀
    -0.96
    avoit
    -0.91
     believes
    -0.89
     considers
    -0.88
     nestled
    -0.87
     weird
    -0.87
     looked
    -0.87
    POSITIVE LOGITS
    actually
    1.06
     cuatro
    0.99
    drawSprites
    0.96
     ridiculously
    0.95
     quintessential
    0.95
     améliorer
    0.95
     créer
    0.93
    intégr
    0.93
     gigantic
    0.93
     trois
    0.93
    Activations Density 0.002%

    No Known Activations