© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7463
    Prev
    Next
    INDEX
    Explanations

    generating content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
    的对象
    0.67
    ۔
    0.67
    :
    0.66
    can
    0.64
    ون
    0.60
     can
    0.58
    यों
    0.57
    о
    0.55
    ib
    0.54
     הג
    0.53
    POSITIVE LOGITS
    生成
    1.06
     generating
    0.96
     Generate
    0.95
     Generated
    0.95
     generates
    0.93
     Generating
    0.91
     generated
    0.89
     generate
    0.88
    Generate
    0.87
     gerar
    0.84
    Activations Density 0.148%

    No Known Activations