© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9952
    Prev
    Next
    INDEX
    Explanations

    image, new, todo, meal

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

    The neuron fires on uppercase technical identifiers or acronyms (e.g. macro/variable names, file‐name fragments, and other all‐caps tokens).

    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_31_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
    -',
    0.93
    -.
    0.90
    -
    0.90
    -}\
    0.89
    -\\
    0.88
    -|
    0.84
    -${
    0.83
    -”
    0.83
    -\
    0.82
    Asimismo
    0.82
    POSITIVE LOGITS
    _
    2.81
    _${
    1.90
    \_
    1.86
    _(
    1.83
    _"+
    1.81
    _%
    1.80
    _"
    1.80
    _$
    1.77
    _[
    1.76
    _",
    1.72
    Activations Density 0.051%

    No Known Activations