© 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. 2811
    Prev
    Next
    INDEX
    Explanations

    "

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

    This neuron activates on opening double‐quote characters marking the start of quoted 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
    and
    0.90
     `=
    0.77
     "'.$
    0.75
     )
    0.75
     ),
    0.75
     [])
    0.72
    IQR
    0.72
    chtigt
    0.71
    ؘ
    0.71
     );
    0.71
    POSITIVE LOGITS
    기
    0.86
    ”（
    0.77
    ”，
    0.68
    出
    0.67
    物
    0.67
    一带
    0.66
    umbrella
    0.64
    唰
    0.63
     Органи
    0.60
    新
    0.60
    Activations Density 0.176%

    No Known Activations