© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15615
    Prev
    Next
    INDEX
    Explanations

    object properties

    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
     üretim
    0.54
     tipo
    0.51
    嚯
    0.50
     داعش
    0.50
    荑
    0.50
     type
    0.50
    Ꮸ
    0.50
    挼
    0.50
     ॥
    0.49
    ్‌
    0.49
    POSITIVE LOGITS
    subtype
    0.61
    豊富な
    0.52
    規模
    0.51
     ONU
    0.49
     Mechanics
    0.48
     subtype
    0.48
    を獲得
    0.48
    тивными
    0.46
    を持ち
    0.46
    SubType
    0.45
    Activations Density 0.106%

    No Known Activations