© 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-262K
    7. 44182
    Prev
    Next
    INDEX
    Explanations

    unusual characters or non-English text

    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_262k_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
     be
    0.38
     provenant
    0.36
     반드시
    0.34
     بواسطة
    0.33
    铍
    0.32
     baff
    0.32
     mencegah
    0.32
     relativement
    0.31
     乀
    0.31
     време
    0.30
    POSITIVE LOGITS
    你知道
    0.39
    ϓ
    0.39
    ोष
    0.39
     |.
    0.37
    АР
    0.37
    |</
    0.37
    Gallery
    0.36
    निर्माण
    0.36
    Л
    0.36
    वायरमेंट
    0.36
    Activations Density 0.027%

    No Known Activations