© 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. 229644
    Prev
    Next
    INDEX
    Explanations

    streaming, shipping, sales

    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
    沧
    0.48
    信号
    0.46
    仡
    0.46
    霓
    0.44
     EXISTING
    0.44
    菱
    0.44
    蝠
    0.43
    <0x8D>
    0.43
     cirrh
    0.43
    蒇
    0.42
    POSITIVE LOGITS
     protection
    0.49
     affaires
    0.49
     affaire
    0.47
     Spanish
    0.46
    cp
    0.46
    port
    0.44
     Standardization
    0.44
     aiding
    0.43
     i
    0.43
     día
    0.43
    Activations Density 0.000%

    No Known Activations