© 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-65K
    7. 3490
    Prev
    Next
    INDEX
    Explanations

    likes and upvotes

    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_65k_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
     bě
    0.38
     पृथ
    0.38
     Dac
    0.37
     канце
    0.37
     transporting
    0.36
     пото
    0.35
     தெளிவாக
    0.35
    孫
    0.35
     దృ
    0.34
    雛
    0.34
    POSITIVE LOGITS
     Likes
    1.57
     liking
    1.44
     likes
    1.43
     liked
    1.42
    Likes
    1.42
    likes
    1.28
     좋아요
    1.28
     लाइक
    1.27
    liked
    1.17
    Liked
    1.17
    Activations Density 0.100%

    No Known Activations