© 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. 1664
    Prev
    Next
    INDEX
    Explanations

    final punctuation or comparison

    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
     Messrs
    0.44
    l
    0.42
     ल
    0.41
    ্ের
    0.39
     일반적으로
    0.39
     ponieważ
    0.38
    ipherals
    0.38
     অন্যান্য
    0.38
     bulunan
    0.38
    mathemat
    0.37
    POSITIVE LOGITS
     galore
    0.68
    ?
    0.68
    ؟
    0.66
    ？
    0.64
    ?!
    0.63
     goes
    0.57
     paradise
    0.56
    ؟!
    0.55
    什么的
    0.54
     conundrum
    0.54
    Activations Density 0.409%

    No Known Activations