© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 583
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    The neuron fires on the punctuation and formatting tokens (semicolons, “pp.”, colons, etc.) that typically appear in academic citation or bibliography entries.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    र्यंत
    0.50
    ᄄ
    0.45
    從
    0.45
     없
    0.43
    ÈME
    0.43
     год
    0.42
     từ
    0.41
    Від
    0.40
    Ό
    0.40
     τα
    0.40
    POSITIVE LOGITS
     io
    0.39
    ↵↵
    0.39
     permissions
    0.38
    अली
    0.37
     negotiator
    0.37
     inquirer
    0.37
     ہیں۔
    0.36
     commander
    0.36
     pubblico
    0.36
     conspir
    0.35
    Activations Density 0.000%

    No Known Activations