© 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. 31-GEMMASCOPE-2-RES-16K
    4. 10968
    Prev
    Next
    INDEX
    Explanations

    media, medical, imaging, screens

    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_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
    Ре
    0.63
    マ
    0.63
    Эта
    0.61
    在日本
    0.57
    ุทธ
    0.57
    shtml
    0.56
    あす楽
    0.56
    מ
    0.56
    quir
    0.55
     эпи
    0.55
    POSITIVE LOGITS
     వ‌
    0.64
     rises
    0.63
     wn
    0.63
     doo
    0.62
    ചര്യ
    0.59
     seawater
    0.59
     pressurized
    0.59
     bijection
    0.59
     buttercream
    0.58
     obstruction
    0.57
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.