© 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. 2171
    Prev
    Next
    INDEX
    Explanations

    status codes or errors

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

    The neuron detects statistical significance expressions, i.e. p-value markers like “p < 0.05.”

    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
     두
    0.59
    ድግዳ
    0.57
     티
    0.55
     manis
    0.49
     två
    0.49
     ও
    0.48
    두
    0.48
     mooring
    0.47
     회
    0.47
     estreno
    0.47
    POSITIVE LOGITS
    。
    0.70
    Other
    0.53
    );
    0.51
    いて
    0.51
    .
    0.51
     Biết
    0.50
     Other
    0.49
     opportune
    0.48
    🤯
    0.47
    ระดับ
    0.47
    Activations Density 0.012%

    No Known Activations