© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25759
    Prev
    Next
    INDEX
    Explanations

    average, particular, Purdue

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

    two children

    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
    Not in Any Lists

    No Comments

    Negative Logits
    全員
    0.46
    قام
    0.44
    ل
    0.44
    و
    0.43
    زمان
    0.43
     contou
    0.43
     aides
    0.42
    %
    0.41
     stranded
    0.41
    定番
    0.41
    POSITIVE LOGITS
     )),
    0.56
     логи
    0.55
    ")),
    0.52
     магнит
    0.51
     જ
    0.50
    óso
    0.48
     पित
    0.47
     রাশি
    0.46
     यूनिवर्सिटी
    0.45
    ẽ
    0.45
    Activations Density 0.000%

    No Known Activations