© 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. 147490
    Prev
    Next
    INDEX
    Explanations

    commencement

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

    compiling source, native Node, vibrator, colleges, manipulated

    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
     kh
    0.51
     quia
    0.51
    ں
    0.46
     diga
    0.45
    łod
    0.43
     głów
    0.43
    لات
    0.43
     Bury
    0.43
     runner
    0.42
     zwar
    0.42
    POSITIVE LOGITS
    yuan
    0.49
     распространен
    0.45
     जरुरी
    0.45
    rails
    0.44
    kker
    0.44
    Lei
    0.44
     канцеля
    0.43
    Ⲣ
    0.43
     Lei
    0.43
    Xinhua
    0.43
    Activations Density 0.000%

    No Known Activations