© 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. 12290
    Prev
    Next
    INDEX
    Explanations

    crypto markets

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

    The neuron strongly activates on unusually rare or infrequent tokens—i.e. words that occur very infrequently in the corpus.

    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
     abrang
    0.76
     gồm
    0.74
     לפי
    0.72
     Несмотря
    0.71
     lakes
    0.71
    .__
    0.68
    loff
    0.68
    stdout
    0.67
     lake
    0.67
     côte
    0.67
    POSITIVE LOGITS
    ше
    0.77
    え
    0.74
    z
    0.74
    ダ
    0.74
    ας
    0.73
    ah
    0.73
    おはよう
    0.73
    o
    0.73
    ть
    0.72
    グ
    0.71
    Activations Density 0.001%

    No Known Activations