© 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. 47989
    Prev
    Next
    INDEX
    Explanations

    code comments and programming language keywords

    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
     percol
    0.45
    ارا
    0.43
     Stacey
    0.42
    gifs
    0.41
    ">
    0.41
     haces
    0.41
     hace
    0.41
    事で
    0.40
    wch
    0.40
     Rhys
    0.40
    POSITIVE LOGITS
    ♎
    0.41
     EDT
    0.38
    Соцмережа
    0.38
     carénés
    0.38
     скульп
    0.38
     engl
    0.38
    ཊ
    0.38
     совме
    0.37
    ್ರಿ
    0.37
     ಆನಿ
    0.37
    Activations Density 0.000%

    No Known Activations