© 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. 15835
    Prev
    Next
    INDEX
    Explanations

    see what

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

    This neuron primarily responds to numerical expressions (i.e. tokens representing numbers or digit sequences).

    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
    j
    0.84
     relevant
    0.73
    لی
    0.72
    nament
    0.72
    یکل
    0.70
    অন
    0.70
     relevante
    0.69
    یر
    0.68
     importantly
    0.68
    বিজ্ঞান
    0.67
    POSITIVE LOGITS
    ၃
    0.79
     соеди
    0.77
    鈽
    0.77
     Probation
    0.77
     cordless
    0.75
    шены
    0.74
    脿
    0.74
    avais
    0.73
     CIRC
    0.73
     tiết
    0.73
    Activations Density 0.001%

    No Known Activations