© 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-16K
    7. 11567
    Prev
    Next
    INDEX
    Explanations

    all versions and entirety

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

    whole, complete, entire

    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_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resa
    0.40
     Einf
    0.40
    
    0.39
    aisseur
    0.38
    䉍
    0.38
     shaped
    0.38
    ೇನೆ
    0.38
     smě
    0.38
     yeah
    0.37
    巨人
    0.37
    POSITIVE LOGITS
     totalidad
    0.55
    ຂ
    0.47
     holistic
    0.45
     Holistic
    0.45
     entirety
    0.43
     All
    0.41
     excepto
    0.41
     Everywhere
    0.41
     GetAll
    0.41
    getValue
    0.41
    Activations Density 0.186%

    No Known Activations