© 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. 229747
    Prev
    Next
    INDEX
    Explanations

    keep calm and

    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
    デ
    0.51
    لی
    0.50
    ردن
    0.48
    ᾳ
    0.46
    ート
    0.46
    evenly
    0.46
    ek
    0.45
     ডিসেম্বর
    0.44
    ଳ
    0.44
    ⇆
    0.44
    POSITIVE LOGITS
     comandante
    0.55
     හා
    0.50
     norte
    0.48
     Kultur
    0.47
     gewährle
    0.47
     Kamer
    0.47
     وغير
    0.47
     Nachricht
    0.46
     rud
    0.46
     Küçük
    0.46
    Activations Density 0.001%

    No Known Activations