© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131415
    Prev
    Next
    INDEX
    Explanations

    GraalVM native compilation

    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_40_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
    жную
    0.41
     xrange
    0.41
     মিলিয়ন
    0.41
     Loma
    0.40
    examine
    0.40
    敺
    0.40
    ﾐ
    0.40
     Examine
    0.39
     सूर्य
    0.39
    ｾ
    0.38
    POSITIVE LOGITS
     Gra
    0.53
    Gra
    0.53
     gra
    0.45
     punctu
    0.42
    Config
    0.41
    gra
    0.41
     gast
    0.39
     configur
    0.39
    SQL
    0.38
    fitting
    0.38
    Activations Density 0.000%

    No Known Activations