© 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. 24-GEMMASCOPE-2-RES-16K
    7. 12073
    Prev
    Next
    INDEX
    Explanations

    Micro, Small, Medium Enterprises; useState; affordability; Open

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

    The neuron responds most strongly to uncommon or low‐frequency tokens (i.e. rare words).

    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
    ’;
    0.80
    }{
    0.79
    ">
    0.75
    ’:
    0.71
    句话
    0.71
    琳
    0.71
    EST
    0.70
     Gop
    0.69
    种类
    0.69
     Takah
    0.68
    POSITIVE LOGITS
    ó
    0.83
    te
    0.80
    dı
    0.80
    ع
    0.79
    ết
    0.77
    ك
    0.76
    lo
    0.75
    шие
    0.74
    섣
    0.73
    daki
    0.72
    Activations Density 0.000%

    No Known Activations