© 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. 113967
    Prev
    Next
    INDEX
    Explanations

    candidates International

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

    I will explain/provide

    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
    енты
    0.57
     می‌شوند
    0.57
    yawa
    0.55
    béco
    0.54
    inę
    0.53
    ơi
    0.52
    Baş
    0.51
    Mana
    0.51
    ǽ
    0.50
    Sala
    0.49
    POSITIVE LOGITS
     f
    0.52
     t
    0.51
     l
    0.48
     Carpet
    0.48
     n
    0.46
    0.46
     United
    0.46
     g
    0.45
     wh
    0.45
     od
    0.44
    Activations Density 0.000%

    No Known Activations