© 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. 10972
    Prev
    Next
    INDEX
    Explanations

    international characters

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

    The neuron is a specialist for the colon character “:,” i.e. it strongly activates on colon tokens (as used in code or line‐label contexts).

    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
    ="("
    0.56
    //=
    0.53
     '='
    0.52
    であることを
    0.51
     handed
    0.50
     magnetometer
    0.50
     ব্লগ
    0.50
    ᅯ
    0.50
     siendo
    0.50
    ='{{
    0.50
    POSITIVE LOGITS
     Dia
    0.64
     Obst
    0.60
     Apart
    0.57
     Conform
    0.57
     Once
    0.55
     Mia
    0.54
     Opportun
    0.54
    Obst
    0.54
    follows
    0.54
    Dia
    0.53
    Activations Density 0.010%

    No Known Activations