© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13446
    Prev
    Next
    INDEX
    Explanations

    the number thirteen

    np_acts-logits-general · gemini-2.5-flash-lite

    13B models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-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
     करके
    0.54
    ان
    0.52
    𝗧
    0.49
    䚺
    0.48
    ین
    0.47
    𝗖
    0.45
    an
    0.45
     Ultimately
    0.45
    0.43
    ֵ
    0.43
    POSITIVE LOGITS
    ри
    0.53
     thirteen
    0.51
    azam
    0.50
    из
    0.49
     wre
    0.49
     Иванов
    0.48
    arent
    0.47
     VID
    0.47
     FR
    0.46
     b
    0.46
    Activations Density 0.166%

    No Known Activations