© 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. 12790
    Prev
    Next
    INDEX
    Explanations

    conditionally renders

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

    The neuron responds to unusually rare or low‐frequency words 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
    厂
    0.91
     Meskipun
    0.85
     sparsim
    0.84
    dna
    0.81
    的不
    0.80
    desi
    0.80
    STA
    0.79
    衊
    0.79
    ATES
    0.79
    REAT
    0.79
    POSITIVE LOGITS
     VERY
    0.77
     cộng
    0.73
     fiberglass
    0.72
     crayons
    0.72
    ___________
    0.72
     sunlight
    0.71
     ২টি
    0.71
    
    0.69
     varnish
    0.68
     grating
    0.68
    Activations Density 0.000%

    No Known Activations