© 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. 10391
    Prev
    Next
    INDEX
    Explanations

    sample questions

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

    The neuron fires most strongly on 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
     tarm
    0.88
     intenso
    0.81
    쳥
    0.81
     sierp
    0.79
    斯的
    0.78
    قبال
    0.77
    ್ಟ
    0.76
     patt
    0.76
     numerosi
    0.76
     senin
    0.74
    POSITIVE LOGITS
    ’
    0.88
    não
    0.78
     Manohar
    0.75
    من
    0.74
    ع
    0.74
    و
    0.73
    ου
    0.73
    .
    0.73
    '
    0.71
    a
    0.70
    Activations Density 0.000%

    No Known Activations