© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48636
    Prev
    Next
    INDEX
    Explanations

    common punctuation and question marks

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

    This neuron responds to emphasis markers in social‐media style text—i.e. question marks, exclamation marks, emojis, and other expressive punctuation.

    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
    inston
    -1.05
    💞
    -1.04
    🤟
    -1.01
    🍼
    -1.01
    🫶
    -1.01
    🍾
    -0.99
    💝
    -0.98
     ken
    -0.98
     Oyun
    -0.97
    💗
    -0.96
    POSITIVE LOGITS
     #
    1.98
     swipe
    1.97
     Swipe
    1.94
    Swipe
    1.86
     @
    1.65
    swipe
    1.65
     .
    1.64
     •
    1.63
    #
    1.62
    •
    1.30
    Activations Density 0.011%

    No Known Activations