© 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. 22638
    Prev
    Next
    INDEX
    Explanations

    levels, increase, domains, improvement

    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
    锶
    0.45
    Motors
    0.44
    ARTS
    0.44
    ILS
    0.43
    Alternatively
    0.42
    砚
    0.42
    Parts
    0.42
    Terrain
    0.42
    മല്ല
    0.41
    Tourist
    0.41
    POSITIVE LOGITS
     فِي
    0.45
     మంత్రి
    0.42
    ឆ្នាំ
    0.40
    spark
    0.39
    ゼン
    0.39
    _{
    0.39
     অস্বাভাবিক
    0.38
    ချင်း
    0.38
     статистика
    0.38
    េង
    0.37
    Activations Density 0.000%

    No Known Activations