© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10965
    Prev
    Next
    INDEX
    Explanations

    fictional story repeats iteratively

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

    The neuron strongly activates on numeric or quantitative expressions (e.g. numbers, percentages, indicators), i.e. it detects tokens representing measurements or counts.

    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
    $^
    0.82
    \
    0.80
    на
    0.77
    তে
    0.74
    রুখ
    0.72
    '/
    0.71
    нё
    0.71
    arelli
    0.71
     밝
    0.70
    isian
    0.69
    POSITIVE LOGITS
    ">=</
    0.84
     Тол
    0.78
     سقوط
    0.77
    Tout
    0.76
    বাধিকার
    0.75
    ChooseCharacter
    0.73
     Når
    0.73
    させていただ
    0.72
     дър
    0.72
    部品
    0.72
    Activations Density 0.000%

    No Known Activations