© 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. 90138
    Prev
    Next
    INDEX
    Explanations

    end of disclaimer

    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
     نئے
    0.48
    細胞
    0.46
     새로운
    0.45
     지나
    0.45
     নতুন
    0.43
    新しい
    0.43
    ی
    0.43
    हत्या
    0.42
     nuovi
    0.42
     nuove
    0.42
    POSITIVE LOGITS
    .--
    0.50
    ຂອງ
    0.45
    ,=
    0.44
    0.43
    ,--
    0.41
    marine
    0.41
    "--
    0.41
    케이
    0.40
    ²,
    0.40
    बांग
    0.40
    Activations Density 0.002%

    No Known Activations