© 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. 135527
    Prev
    Next
    INDEX
    Explanations

    identify identify ideas

    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
     boarding
    0.48
    ProjectPath
    0.48
     ถ้า
    0.47
     إذا
    0.45
     यदि
    0.44
    ٺ
    0.44
    centered
    0.44
     اذا
    0.44
     może
    0.44
     اگر
    0.43
    POSITIVE LOGITS
    êmica
    0.50
    울
    0.43
    ьев
    0.42
    Hunt
    0.42
     tropes
    0.42
     मर्दों
    0.41
    ット
    0.41
    हेज
    0.41
     явления
    0.41
    熟悉
    0.40
    Activations Density 0.002%

    No Known Activations