© 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. 102963
    Prev
    Next
    INDEX
    Explanations

    application project template design

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

    app and application creation

    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
     effectiveness
    0.49
    ^{*}}{\
    0.48
     succede
    0.47
     durumu
    0.46
    effectiveness
    0.46
    ^{*}}\
    0.45
    larghezza
    0.45
    rats
    0.44
    ড়াল
    0.44
    ések
    0.44
    POSITIVE LOGITS
    SA
    0.49
    Retail
    0.45
    牺
    0.44
    SW
    0.44
     playable
    0.42
    SX
    0.42
    普通の
    0.42
    BS
    0.41
     Ordinary
    0.40
    IGA
    0.40
    Activations Density 0.000%

    No Known Activations