© 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. 10066
    Prev
    Next
    INDEX
    Explanations

    final amount, mass, energy, sum

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

    The neuron activates on numerical quantities—especially decimal numbers representing measurements or amounts.

    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
     Якщо
    0.74
     Temperatur
    0.71
    ˏ
    0.71
     sitzen
    0.70
    verage
    0.68
     Eintrag
    0.67
    Temper
    0.66
    phalodes
    0.65
    TAT
    0.64
     Jeżeli
    0.64
    POSITIVE LOGITS
    最终
    0.71
    ivé
    0.71
    }^{+},
    0.70
    新た
    0.68
    фин
    0.68
    お得
    0.68
     funds
    0.66
    成果
    0.66
    返回
    0.65
    اتی
    0.65
    Activations Density 0.000%

    No Known Activations