© 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. 100905
    Prev
    Next
    INDEX
    Explanations

    property cannot

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

    procedures and making changes

    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
     ček
    0.49
     intravenously
    0.48
    ￠
    0.48
     Contin
    0.48
     przygot
    0.48
     BYU
    0.46
     cinch
    0.46
     السيارة
    0.46
    삑
    0.46
    ινε
    0.45
    POSITIVE LOGITS
    CallBack
    0.48
    IllegalArgument
    0.45
    Schema
    0.45
    </code>
    0.44
    ${
    0.42
    ows
    0.41
     //}
    0.41
    orient
    0.41
    ipynb
    0.41
    Ill
    0.40
    Activations Density 0.001%

    No Known Activations