© 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-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15205
    Prev
    Next
    INDEX
    Explanations

    field names Q and Z

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     homomorphisms
    0.61
    ṭ
    0.60
     आवड
    0.59
     кноп
    0.58
     FON
    0.58
     compon
    0.57
     squat
    0.57
    獻
    0.56
     समीकरण
    0.56
     выбран
    0.56
    POSITIVE LOGITS
    Anon
    0.54
     Оксана
    0.54
    :
    0.52
    Deep
    0.52
    Man
    0.50
    Ocean
    0.50
    World
    0.48
    Lance
    0.48
    Roger
    0.47
    pipeline
    0.47
    Activations Density 0.002%

    No Known Activations