© 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. 167759
    Prev
    Next
    INDEX
    Explanations

    own design and assembly

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

    specific abbreviations and qualifiers

    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
    )
    0.48
    riften
    0.47
    )==
    0.43
    elés
    0.43
     bencana
    0.42
    疝
    0.41
     দা
    0.41
     Morse
    0.41
    ):
    0.40
     മതി
    0.40
    POSITIVE LOGITS
    за
    0.50
     Isol
    0.49
    ס
    0.48
    ייס
    0.47
     royals
    0.47
     kwamba
    0.47
     vergang
    0.47
    Hlav
    0.47
     центре
    0.46
    CONCLUS
    0.46
    Activations Density 0.000%

    No Known Activations