© 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. 19319
    Prev
    Next
    INDEX
    Explanations

    variation and ranges

    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
    ❽
    0.43
     Неза
    0.42
     충분
    0.40
    AppBsky
    0.40
     অপ্র
    0.39
     Oğ
    0.39
     जडेजा
    0.39
    िज्या
    0.38
     Dernière
    0.38
     পর্যাপ্ত
    0.38
    POSITIVE LOGITS
     +/-
    0.51
     lows
    0.50
     individual
    0.47
     deviation
    0.47
     extremes
    0.46
     +-
    0.46
     variation
    0.46
     shorter
    0.44
     nearer
    0.43
     varia
    0.43
    Activations Density 0.071%

    No Known Activations