© 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. 7931
    Prev
    Next
    INDEX
    Explanations

    risks associated with

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

    The neuron strongly activates on tokens that are numbers or contain digits.

    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
    ◌
    0.77
    YM
    0.77
     Résultats
    0.77
     Ту
    0.75
     Те
    0.73
              
    0.71
    ______
    0.71
     PLUGIN
    0.70
     אחת
    0.70
     REFERENCES
    0.70
    POSITIVE LOGITS
    ном
    0.74
    জন
    0.72
    ጕ
    0.71
    哞
    0.71
    ực
    0.70
    balanced
    0.70
    სა
    0.70
    ধার
    0.70
    umbled
    0.69
    manship
    0.69
    Activations Density 0.000%

    No Known Activations