© 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. 7284
    Prev
    Next
    INDEX
    Explanations

    Core g coc

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

    The neuron fires on the opening double‐quote character that introduces a title or caption (e.g. the start of a quoted gallery or post title).

    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
     Incorrect
    0.88
    ASTIC
    0.84
     goodies
    0.77
    Incorrect
    0.73
    untary
    0.72
    殃
    0.72
     IBS
    0.71
    """.
    0.71
     inelastic
    0.71
     "#{
    0.71
    POSITIVE LOGITS
     gestão
    0.85
     conductores
    0.84
    시
    0.81
    お待ち
    0.80
    องค์
    0.79
    ли
    0.79
     सहयोग
    0.78
    it
    0.77
     Tổ
    0.75
     управління
    0.74
    Activations Density 0.001%

    No Known Activations