© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8720
    Prev
    Next
    INDEX
    Explanations

    code printing and returning values

    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_40_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
    женности
    0.35
    很快
    0.34
    あなたが
    0.34
    ڳ
    0.33
    ʎ
    0.33
    зной
    0.33
    міст
    0.33
    Este
    0.32
     টিভির
    0.32
     للخ
    0.32
    POSITIVE LOGITS
    atin
    0.42
    upport
    0.38
    neider
    0.38
    anda
    0.38
    {}".
    0.38
    ara
    0.38
    aren
    0.37
     thereof
    0.37
     właśnie
    0.37
    ata
    0.37
    Activations Density 0.827%

    No Known Activations