© 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-16K
    7. 5278
    Prev
    Next
    INDEX
    Explanations

    time durations and calculations

    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_16k_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
    Η
    0.46
    ﾗ
    0.42
     प्रतिदिन
    0.41
    со
    0.41
    線
    0.41
    ﾘ
    0.41
    ijos
    0.40
    Г
    0.40
    rim
    0.40
     opcoes
    0.40
    POSITIVE LOGITS
     anderes
    0.39
     therefor
    0.39
     anything
    0.38
     الأخرى
    0.38
     wrenches
    0.38
     counterpart
    0.37
     counterv
    0.36
     fellow
    0.36
     نفسها
    0.36
     hiszen
    0.36
    Activations Density 0.199%

    No Known Activations