© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 80793
    Prev
    Next
    INDEX
    Explanations

    translations and processes

    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
    Negative Logits
    ↵
    0.54
     tranquil
    0.45
     retained
    0.45
     pleasant
    0.44
     hor
    0.44
     *
    0.42
     brought
    0.42
     comforting
    0.41
     mill
    0.41
     Trump
    0.41
    POSITIVE LOGITS
    śl
    0.56
     осна
    0.54
     कायदा
    0.54
    கடந்த
    0.53
    ۹
    0.53
    apopt
    0.51
     አመ
    0.51
    伝説
    0.51
    鲐
    0.51
    rtol
    0.51
    Activations Density 0.005%

    No Known Activations