© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 102817
    Prev
    Next
    INDEX
    Explanations

    examples under

    np_acts-logits-general · gemini-2.5-flash-lite

    LLaMA model

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     sponge
    0.54
    ،
    0.49
     spongy
    0.46
     ruthless
    0.45
     inade
    0.45
     dépens
    0.44
     stup
    0.44
    我对
    0.44
     hazy
    0.43
     aliment
    0.43
    POSITIVE LOGITS
     =
    0.53
     czyli
    0.50
     DISPLAYS
    0.46
     यानी
    0.45
     delivers
    0.45
    announce
    0.45
    診
    0.44
     ০
    0.44
        
    0.44
     Batik
    0.44
    Activations Density 0.001%

    No Known Activations