© 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. 152994
    Prev
    Next
    INDEX
    Explanations

    byproduct or residual material

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

    producing water and oxygen

    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
    性价比
    0.46
     نہایت
    0.45
    перы
    0.44
    东北
    0.43
     طريقة
    0.41
     способов
    0.41
    രുന്ന
    0.40
    шают
    0.40
    选取
    0.40
    选
    0.39
    POSITIVE LOGITS
     debris
    0.52
     residual
    0.52
     feces
    0.49
     leftover
    0.48
     Residual
    0.47
     syslog
    0.47
     leaving
    0.45
     meninggalkan
    0.45
    debris
    0.45
    residual
    0.45
    Activations Density 0.022%

    No Known Activations