© 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. 187323
    Prev
    Next
    INDEX
    Explanations

    existence and dialogue

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

    Pointer arithmetic and polite declining

    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
     Kathryn
    0.48
     Seymour
    0.47
    াগর
    0.46
    ా
    0.45
    鳌
    0.44
     întâ
    0.44
     adjourn
    0.43
     originals
    0.42
    桥
    0.41
    公斤
    0.41
    POSITIVE LOGITS
    esistenza
    0.50
     따라서
    0.48
     例えば
    0.47
    }:\
    0.45
    álogo
    0.45
    存在
    0.44
     स्मरण
    0.42
    exist
    0.42
     ઉપયોગ
    0.41
    存在する
    0.41
    Activations Density 0.000%

    No Known Activations