© 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. 169293
    Prev
    Next
    INDEX
    Explanations

    moving piece multiple times

    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
     excit
    0.39
     evolved
    0.39
    橑
    0.38
    ތ
    0.38
     nhật
    0.38
     அளவுக்கு
    0.38
    ထား
    0.37
     흥
    0.37
     subscribers
    0.37
    λύ
    0.37
    POSITIVE LOGITS
     ț
    0.40
    えた
    0.40
    Denied
    0.39
    Mogo
    0.37
    acağı
    0.37
     어렵
    0.37
     Government
    0.36
     اکرم
    0.36
     Keg
    0.35
     काळ
    0.35
    Activations Density 0.002%

    No Known Activations