© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 671
    Prev
    Next
    INDEX
    Explanations

    bullet points and special characters

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

    The neuron is triggered by unusual non-ASCII or special typographic tokens (e.g. stray backticks, accented characters, or other odd Unicode punctuation).

    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
     axial
    0.54
    \\
    0.49
    y
    0.46
     {
    0.46
     crum
    0.45
     Eiffel
    0.45
    \
    0.45
     chunk
    0.45
     UNIX
    0.45
     Axial
    0.45
    POSITIVE LOGITS
    า
    0.73
    했다
    0.67
     黃
    0.66
    IAN
    0.66
    Escolhido
    0.66
    授予
    0.65
     prácticamente
    0.62
     únicamente
    0.61
     econôm
    0.61
     ダイニング
    0.61
    Activations Density 0.000%

    No Known Activations