© 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. 5206
    Prev
    Next
    INDEX
    Explanations

    retracted due to

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

    The neuron fires on numeric tokens—especially floating‐point numbers—i.e. decimal measurements or similar numerical values 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
    да
    0.94
    ia
    0.87
     pierced
    0.86
    un
    0.83
    ol
    0.80
    tropical
    0.77
    м
    0.77
    ad
    0.76
    ла
    0.76
    syringe
    0.76
    POSITIVE LOGITS
     namens
    0.97
    வையான
    0.92
     folgen
    0.91
     Teilnahme
    0.90
     Tabelle
    0.88
    عل
    0.86
    があります
    0.85
     eignet
    0.83
     entscheiden
    0.83
     humaine
    0.82
    Activations Density 0.001%

    No Known Activations