© 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. 246793
    Prev
    Next
    INDEX
    Explanations

    for educational purposes

    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
     البعض
    0.46
    も
    0.44
     بف
    0.43
    することで
    0.42
    ൌ
    0.41
    哣
    0.41
     corral
    0.40
    ⃖
    0.40
    عتها
    0.40
     appunto
    0.39
    POSITIVE LOGITS
    Context
    0.49
    rcode
    0.47
    字节
    0.46
    cw
    0.46
    endung
    0.46
    ajā
    0.45
     kē
    0.44
     icch
    0.44
     felicit
    0.44
    CONTEXT
    0.43
    Activations Density 0.001%

    No Known Activations