© 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. 10917
    Prev
    Next
    INDEX
    Explanations

    special characters and code syntax

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

    The neuron is broadly triggered by very frequent, generic tokens (common words and short unit markers) that recur across different contexts.

    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
     L
    0.77
     এলি
    0.75
     Gr
    0.75
     C
    0.74
    com
    0.74
    ferencia
    0.73
     Pon
    0.72
    ally
    0.72
     Steps
    0.72
     with
    0.71
    POSITIVE LOGITS
    ين
    0.85
    Marne
    0.84
    theless
    0.83
    팥
    0.81
    IRA
    0.78
    फेसर
    0.78
    唥
    0.78
    ंदाज
    0.77
    HAD
    0.77
    Rahul
    0.76
    Activations Density 0.000%

    No Known Activations