© 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. 197265
    Prev
    Next
    INDEX
    Explanations

    Facebook or comments

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

    social and economic benefits

    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
     дополнительные
    0.54
     ஆண்
    0.50
     подобные
    0.48
     подклю
    0.48
    চর্
    0.48
    Ἑ
    0.48
     кня
    0.48
     наказа
    0.48
     муж
    0.47
     просты
    0.47
    POSITIVE LOGITS
    0.52
    n
    0.52
     n
    0.50
    ser
    0.49
    سن
    0.48
     to
    0.48
     Initiative
    0.46
    il
    0.45
    ut
    0.45
     Azul
    0.45
    Activations Density 0.000%

    No Known Activations