© 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. 36077
    Prev
    Next
    INDEX
    Explanations

    strikethrough text

    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
    Independent
    0.44
    Violence
    0.42
    ാവുന്ന
    0.40
    哎
    0.40
    
    0.40
    佝
    0.39
    冚
    0.38
    涳
    0.38
     независи
    0.38
    刊行
    0.37
    POSITIVE LOGITS
     stri
    0.54
     bens
    0.45
     designation
    0.42
     strike
    0.41
     decoration
    0.41
     striker
    0.40
     tras
    0.39
     moist
    0.39
     normal
    0.38
     ric
    0.38
    Activations Density 0.001%

    No Known Activations