© 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. 7135
    Prev
    Next
    INDEX
    Explanations

    Explanation

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

    The neuron fires on numerical tokens—especially multi‐digit numbers or numbered references used for figures, definitions, lemmas, and sections.

    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
     بہانہ
    0.61
    assertion
    0.59
    function
    0.57
    特
    0.57
    then
    0.54
    definitions
    0.53
    結
    0.53
    Theorem
    0.52
    methods
    0.52
     function
    0.52
    POSITIVE LOGITS
     relevantes
    0.66
    }[
    0.65
     nước
    0.64
     melanogaster
    0.64
    }_{[
    0.64
    $_{
    0.64
     #${
    0.63
     インテリア
    0.63
    }:$
    0.62
     proguardFiles
    0.62
    Activations Density 0.011%

    No Known Activations