© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15234
    Prev
    Next
    INDEX
    Explanations

    CROSS_COMPILE, exports, id

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

    this neuron fires on the first nontrivial word at the start of a new paragraph or section.

    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
    لين
    0.72
    پار
    0.70
    Changing
    0.70
    NSURL
    0.67
    ن
    0.66
    lás
    0.66
    Playing
    0.65
    Funny
    0.64
    ("/");
    0.64
    Surf
    0.64
    POSITIVE LOGITS
    ’
    0.90
    tn
    0.85
    ときの
    0.85
     Rồi
    0.81
    ii
    0.80
    相应的
    0.79
    %
    0.79
    ことになる
    0.78
     परसेंट
    0.76
    ski
    0.75
    Activations Density 0.000%

    No Known Activations