© 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. 5103
    Prev
    Next
    INDEX
    Explanations

    taller male

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

    The neuron is tuned to detect numeric tokens with decimal points (floating‐point numbers).

    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
    ним
    0.71
    0
    0.71
    Altri
    0.71
    9
    0.70
     finalmente
    0.70
    Giving
    0.70
    litre
    0.68
     अभिन्न
    0.68
    ยัง
    0.67
    might
    0.67
    POSITIVE LOGITS
    ä
    0.99
     internas
    0.81
     racionais
    0.79
    ermann
    0.77
     ইহাদের
    0.76
    тына
    0.75
     მდ
    0.75
     рекомендуется
    0.75
     iguais
    0.74
    чные
    0.73
    Activations Density 0.001%

    No Known Activations