© 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-16K
    7. 8378
    Prev
    Next
    INDEX
    Explanations

    I understand

    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_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
     الكامل
    0.46
     የግ
    0.46
    щего
    0.45
     በቀ
    0.44
    пта
    0.44
    ⬅
    0.43
     ലഭ്യ
    0.42
     максимально
    0.42
     საჭ
    0.42
    🫠
    0.41
    POSITIVE LOGITS
     grew
    0.41
     ~=
    0.38
     spoken
    0.37
     tell
    0.37
    ได้รับ
    0.37
     experienced
    0.37
     reincarn
    0.36
    experienced
    0.36
    曾经
    0.36
     frust
    0.35
    Activations Density 0.213%

    No Known Activations