© 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. 208068
    Prev
    Next
    INDEX
    Explanations

    dipping sauce, installation, clinics, below

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

    analysis and understanding

    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
     rejoindre
    0.55
    م
    0.51
     концов
    0.49
     "'.$
    0.47
     رو
    0.47
     서버
    0.47
     ஆகவே
    0.45
    벍
    0.45
     мра
    0.44
     подгото
    0.44
    POSITIVE LOGITS
    AB
    0.55
    iting
    0.51
    paro
    0.50
     as
    0.49
    ase
    0.49
    {
    0.48
     bahawa
    0.48
    amento
    0.47
    spin
    0.46
    -
    0.46
    Activations Density 0.000%

    No Known Activations