© 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. 145052
    Prev
    Next
    INDEX
    Explanations

    fast, faster, quickly

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

    iteration and stages

    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
     sollten
    0.51
    ფ
    0.48
     âgé
    0.47
     oscillate
    0.46
     hát
    0.45
     zoon
    0.45
     âg
    0.45
     nobody
    0.44
     diálogo
    0.44
    ق
    0.44
    POSITIVE LOGITS
    スタンダ
    0.45
    我們的
    0.45
     ನಾವು
    0.44
    ・
    0.44
    ra
    0.43
    '&
    0.43
     naszego
    0.43
     午
    0.43
     ہماری
    0.42
     chadd
    0.42
    Activations Density 0.000%

    No Known Activations