© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    aspect ratio, parameters

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

    The neuron fires on repeated dash tokens (e.g. “--”), i.e. document section or break markers.

    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
    ORT
    0.77
    ുന്ന
    0.73
    nych
    0.73
    좀
    0.73
    wic
    0.72
    amps
    0.72
    ਾਂ
    0.70
    ING
    0.69
    EM
    0.67
    cus
    0.66
    POSITIVE LOGITS
    ..--
    0.87
     avevo
    0.85
    ри
    0.82
    ро
    0.81
    ..--..--
    0.81
    .--
    0.81
    ,--
    0.79
    Ꮥ
    0.77
    يه
    0.76
    ⤒
    0.76
    Activations Density 0.047%

    No Known Activations