© 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. 152864
    Prev
    Next
    INDEX
    Explanations

    professionally throughout

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

    phrases starting with common words

    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
     공격
    0.50
     shit
    0.46
     uptime
    0.45
     rigs
    0.44
     endgame
    0.44
     badass
    0.44
     haters
    0.43
     tantrums
    0.42
     fuck
    0.42
     향
    0.42
    POSITIVE LOGITS
    难道
    0.41
     எத்தனை
    0.41
     reminder
    0.40
     чове
    0.40
    的感觉
    0.40
     ilişkin
    0.40
     WHY
    0.38
    নিবেশ
    0.38
    ATHER
    0.38
    Could
    0.38
    Activations Density 0.001%

    No Known Activations