© 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. 12-GEMMASCOPE-2-RES-16K
    7. 235
    Prev
    Next
    INDEX
    Explanations

    "feder revolutionized bath"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    𝐬
    0.79
    ς
    0.76
    ség
    0.70
    s
    0.70
    𝘀
    0.68
    THING
    0.61
    𝐭
    0.61
    ことが多い
    0.59
    ات
    0.58
    ों
    0.55
    POSITIVE LOGITS
    কে
    0.70
    an
    0.66
    ಾ
    0.59
    ور
    0.58
    ーション
    0.55
    zelfde
    0.55
    ри
    0.54
    р
    0.53
    ー
    0.52
    ра
    0.51
    Activations Density 1.135%

    No Known Activations