© 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-65K
    7. 52779
    Prev
    Next
    INDEX
    Explanations

    mix well, returns

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ждении
    0.54
     чув
    0.54
     dará
    0.51
     calme
    0.50
     panas
    0.49
    тон
    0.47
     dė
    0.46
    вли
    0.46
    唏
    0.45
     heartache
    0.45
    POSITIVE LOGITS
     IoT
    0.52
     ability
    0.46
     enabled
    0.46
     businesses
    0.45
    IoT
    0.45
     Enterprise
    0.45
     to
    0.44
     generate
    0.44
     వారికి
    0.44
     touristic
    0.44
    Activations Density 0.030%

    No Known Activations