© 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. 54738
    Prev
    Next
    INDEX
    Explanations

    using powers

    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
    ,
    0.51
    import
    0.49
     were
    0.46
    x
    0.46
     them
    0.46
     by
    0.45
     instead
    0.44
    يز
    0.44
    .
    0.43
    يس
    0.43
    POSITIVE LOGITS
    lüğ
    0.50
     விளக்கம்
    0.49
     Опреде
    0.48
     နောက်
    0.48
     শারীরিক
    0.46
    ﻯ
    0.46
     पढ़े
    0.45
     検
    0.45
     کھیلو
    0.45
     வணக்கம்
    0.45
    Activations Density 0.001%

    No Known Activations