© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11997
    Prev
    Next
    INDEX
    Explanations

    into

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

    The neuron detects tokens that start new sentences or text segments.

    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
    O
    0.84
    I
    0.84
     Bek
    0.81
     мой
    0.81
    E
    0.80
    U
    0.79
     сейчас
    0.77
     rappelle
    0.77
     sabemos
    0.75
     разработан
    0.75
    POSITIVE LOGITS
    tops
    0.89
    损
    0.84
    灌
    0.76
     enhancers
    0.76
    pipes
    0.75
     conduits
    0.73
    electronics
    0.72
    troops
    0.72
    alarına
    0.71
    courts
    0.71
    Activations Density 0.001%

    No Known Activations