© 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. 2031
    Prev
    Next
    INDEX
    Explanations

    data structures and code

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

    The neuron fires on code‐documentation headings or section titles (e.g. “Methods”, “Definition”, “Delegation internal constructor”, “Book resource”, etc.)

    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
    0.85
    L
    0.66
     $\
    0.66
    V
    0.65
    .
    0.59
    ,
    0.59
    B
    0.55
    D
    0.54
     $
    0.51
    1
    0.51
    POSITIVE LOGITS
    ämään
    0.77
    kében
    0.77
     عشان
    0.72
     براي
    0.72
     ciudadanía
    0.69
    īt
    0.68
     ដើម្បី
    0.68
     દ્વારા
    0.66
    utiliser
    0.66
    rät
    0.66
    Activations Density 0.001%

    No Known Activations