© 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. 72731
    Prev
    Next
    INDEX
    Explanations

    weekly impressions

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

    but still, but demonstrates

    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
     غ
    0.46
     перший
    0.43
     B
    0.43
     περι
    0.42
     первый
    0.42
     η
    0.42
     ­
    0.40
     Arap
    0.40
    sieh
    0.40
     Lincoln
    0.40
    POSITIVE LOGITS
    队伍
    0.52
     cruel
    0.50
    "。
    0.46
    的要求
    0.45
    ັກ
    0.45
    威
    0.43
    لان
    0.42
     milik
    0.42
    冷
    0.42
    我们需要
    0.42
    Activations Density 0.001%

    No Known Activations