© 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. 31-GEMMASCOPE-2-RES-262K
    7. 81889
    Prev
    Next
    INDEX
    Explanations

    giving warnings, impressions, and disclaimers

    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
    >∕</
    0.49
     곡
    0.49
     වශයෙන්
    0.49
    ısıyla
    0.48
     რაც
    0.47
    மாகவும்
    0.46
     শূন্য
    0.46
    бычно
    0.46
    juč
    0.46
    ல்லாம்
    0.46
    POSITIVE LOGITS
     شبه
    0.44
    دى
    0.43
     -
    0.43
    掛け
    0.42
     |
    0.42
     :
    0.41
     --
    0.41
     eco
    0.41
     Local
    0.40
     Workplace
    0.40
    Activations Density 0.002%

    No Known Activations