© 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. 20562
    Prev
    Next
    INDEX
    Explanations

    probable cause, larger number, opportunity to

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

    specific example lists

    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
    érard
    0.48
    ího
    0.48
    urian
    0.46
    air
    0.46
    ู
    0.45
     shrub
    0.44
    empire
    0.44
     മേഖ
    0.44
    é
    0.44
    囉
    0.43
    POSITIVE LOGITS
    বলের
    0.50
    ヤマハ
    0.49
     definición
    0.48
    アド
    0.46
    SqlConnection
    0.46
    ционными
    0.44
     பால்
    0.44
     التعريف
    0.43
    ﺫ
    0.43
    ৫৮
    0.42
    Activations Density 0.000%

    No Known Activations