© 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. 36419
    Prev
    Next
    INDEX
    Explanations

    Christian nation

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

    Version numbers and legal documents

    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
     of
    0.50
    ك
    0.49
     निर्देशक
    0.47
    equival
    0.45
     unico
    0.45
    Winter
    0.44
    都可以
    0.44
     ل
    0.44
    Regist
    0.43
     registers
    0.43
    POSITIVE LOGITS
    zuoye
    0.48
     Fang
    0.47
     Phương
    0.45
     fabs
    0.45
    の設定
    0.45
    iposa
    0.44
    ubishi
    0.44
     йөкләү
    0.44
     #{@
    0.44
     Aws
    0.44
    Activations Density 0.000%

    No Known Activations