© 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. 8019
    Prev
    Next
    INDEX
    Explanations

    change

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

    change

    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
     are
    0.45
     homologs
    0.44
     supernatants
    0.44
     مشکلات
    0.44
    \}.
    0.44
    </th>
    0.43
    errors
    0.43
     سعودی
    0.43
    </h2>
    0.43
    "];
    0.42
    POSITIVE LOGITS
     Change
    0.91
     changé
    0.90
     Changed
    0.88
    改变
    0.86
     Changing
    0.86
    Change
    0.86
     changed
    0.85
     change
    0.83
     changing
    0.83
     ändern
    0.82
    Activations Density 0.157%

    No Known Activations