© 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-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8539
    Prev
    Next
    INDEX
    Explanations

    legal or technical documents

    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
    ()
    0.49
     cả
    0.46
    ii
    0.45
    S
    0.44
    这里
    0.44
    atore
    0.43
     ti
    0.42
    uy
    0.42
    iy
    0.42
    ’
    0.42
    POSITIVE LOGITS
    𝗳
    0.42
     wickedness
    0.41
     mengucapkan
    0.39
    慘
    0.38
     harmonies
    0.38
    ফুজ
    0.38
     mutter
    0.38
     Перейти
    0.38
    𝙛
    0.37
     menyampaikan
    0.37
    Activations Density 0.065%

    No Known Activations