© 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. 81926
    Prev
    Next
    INDEX
    Explanations

    following studies and substances

    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
    無論
    0.42
    osphere
    0.39
    including
    0.39
    सभी
    0.39
    met
    0.38
    ?),
    0.38
     Often
    0.38
     ឬ
    0.38
     (
    0.38
     अल
    0.37
    POSITIVE LOGITS
    如下
    0.56
     다음과
    0.50
    有两种
    0.50
     নিম্নলিখিত
    0.48
     folgender
    0.46
    。《
    0.45
     ดัง
    0.45
     följande
    0.42
     berikut
    0.42
     electrically
    0.41
    Activations Density 0.687%

    No Known Activations