© 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. 31-GEMMASCOPE-2-RES-16K
    7. 101
    Prev
    Next
    INDEX
    Explanations

    ASCII art drawing representations, symbols, or characters

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

    This neuron activates on enumeration markers—tokens used to denote list items (bullets, numeric or roman numerals, and the punctuation that commonly prefixes them).

    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_31_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
     analytics
    0.54
     encrypted
    0.49
     😉
    0.47
     encryption
    0.47
     glitch
    0.47
     🙂
    0.45
     geospatial
    0.45
     изначально
    0.45
     nutzen
    0.45
    🌐
    0.44
    POSITIVE LOGITS
    J
    0.63
    U
    0.54
    r
    0.52
    B
    0.52
     Jl
    0.51
    Jl
    0.51
    L
    0.50
    P
    0.50
    I
    0.49
    N
    0.49
    Activations Density 0.169%

    No Known Activations