© 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. 16009
    Prev
    Next
    INDEX
    Explanations

    storyboardWithName OR Process

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

    Flask and ArgumentParser initialization

    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
    ahy
    0.47
    akur
    0.44
    asilkan
    0.43
    ikhil
    0.43
     আরে
    0.43
    hran
    0.42
    ieli
    0.41
    🕺
    0.39
     Kohli
    0.39
     ゆ
    0.39
    POSITIVE LOGITS
    ीट
    0.43
    不禁
    0.40
    プ
    0.39
    ();
    0.38
    для
    0.38
    。
    0.38
    璞
    0.37
     karış
    0.37
    元
    0.37
    امة
    0.37
    Activations Density 0.000%

    No Known Activations