© 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. 624
    Prev
    Next
    INDEX
    Explanations

    mention without

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

    The neuron specializes in spotting parenthetical or quoted asides (tokens like “(” or opening quotation marks).

    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
     แต่
    0.36
     ดังนั้น
    0.33
     it
    0.33
     können
    0.32
                  
    0.31
     adalah
    0.31
     (_
    0.31
           
    0.31
              
    0.30
     เพียง
    0.30
    POSITIVE LOGITS
    non
    0.36
    empirical
    0.35
    %),
    0.34
    applicable
    0.34
    hereafter
    0.34
     acronym
    0.33
    commonly
    0.33
    operational
    0.33
    other
    0.33
    %).
    0.32
    Activations Density 0.456%

    No Known Activations