© 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. 136158
    Prev
    Next
    INDEX
    Explanations

    * before conjunctions, mastery, Japanese, TC, JAM, expected

    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
     republiky
    0.49
     menit
    0.49
     lugar
    0.48
     Uzbek
    0.48
     Leder
    0.48
     يص
    0.48
    ﺓ
    0.48
     mediana
    0.47
     sempat
    0.46
     alue
    0.46
    POSITIVE LOGITS
    心
    0.53
     accents
    0.48
    거운
    0.48
    大
    0.48
    dic
    0.47
    有
    0.46
    用
    0.45
    动
    0.45
    言
    0.45
    眼
    0.44
    Activations Density 0.000%

    No Known Activations