© 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. 143048
    Prev
    Next
    INDEX
    Explanations

    latest trends

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

    concepts and their context

    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
    練習
    0.47
    腃
    0.47
    ام
    0.46
    Boxing
    0.45
    狧
    0.45
    仲
    0.44
    睒
    0.44
    </em>
    0.44
    どこ
    0.44
    創建
    0.44
    POSITIVE LOGITS
    roga
    0.50
    ,,
    0.49
    ród
    0.45
    roqu
    0.45
    ness
    0.45
    '].
    0.44
     symbol
    0.44
    ोजा
    0.44
     trampled
    0.43
     ze
    0.43
    Activations Density 0.000%

    No Known Activations