© 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. 92374
    Prev
    Next
    INDEX
    Explanations

    sequences before common words

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

    begin re-establishing, practiced polygamy

    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
     Israel
    0.49
     kilometres
    0.48
    va
    0.47
     Mittel
    0.47
     immigrants
    0.47
     victims
    0.46
    vou
    0.45
     juxtap
    0.43
    scatterplot
    0.43
    唉
    0.43
    POSITIVE LOGITS
     ልዩ
    0.51
     Официа
    0.51
    ByURL
    0.48
    UTHERN
    0.48
    inoceros
    0.47
    ToFile
    0.46
     言っ
    0.46
     دارید
    0.45
    htaking
    0.45
    כה
    0.44
    Activations Density 0.000%

    No Known Activations