© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33364
    Prev
    Next
    INDEX
    Explanations

    confidentiality, email subjects, or system messages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ୈ
    -1.78
    。　　
    -1.75
    〜。
    -1.71
     of
    -1.69
     just
    -1.66
    って思
    -1.66
     車場
    -1.55
    Obrázky
    -1.53
     for
    -1.52
    ～。
    -1.51
    POSITIVE LOGITS
    すっ
    2.06
    ところに
    2.02
    感じが
    1.98
    ことも
    1.96
    感じで
    1.91
    えっ
    1.82
    急に
    1.81
    感じです
    1.77
    事も
    1.73
    遠い
    1.71
    Activations Density 0.009%

    No Known Activations