© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7654
    Prev
    Next
    INDEX
    Explanations

    melted butter

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

    The neuron selectively detects numerical tokens—especially reference and verse numbers—embedded in the text.

    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
    en
    0.82
    icago
    0.70
    м
    0.69
     organisations
    0.64
    zes
    0.64
    q
    0.64
    us
    0.63
    az
    0.63
    em
    0.63
    ored
    0.63
    POSITIVE LOGITS
    <unused515>
    0.90
     Также
    0.86
    BUGFS
    0.83
    ﺸ
    0.82
    グリップ
    0.80
     Gutiérrez
    0.80
     После
    0.80
    ্্
    0.79
     Reese
    0.79
    Τα
    0.77
    Activations Density 0.001%

    No Known Activations