© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    file on video

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

    The neuron strongly activates on long dash or em‐dash characters (extended punctuation marks) in the text.

    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
     ח
    0.85
    ד
    0.85
    ח
    0.77
     CHARACTER
    0.75
     Accessed
    0.75
     remainder
    0.75
    ↵↵
    0.70
     اﻷ
    0.69
     תו
    0.68
    ↵
    0.66
    POSITIVE LOGITS
    zeti
    0.80
     Saheb
    0.80
    ↺
    0.79
     abbey
    0.79
    アルバム
    0.78
    ма
    0.78
     jours
    0.77
    យើង
    0.75
    objc
    0.75
    jours
    0.75
    Activations Density 0.000%

    No Known Activations