© 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. 98795
    Prev
    Next
    INDEX
    Explanations

    python `__repr__` f-strings

    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
     funcion
    0.41
    وترات
    0.41
    ⱼ
    0.41
     przes
    0.40
     ekspl
    0.40
     Drawable
    0.40
     satisfait
    0.40
     dimensi
    0.40
     porówn
    0.40
     scalars
    0.39
    POSITIVE LOGITS
    ajax
    0.43
     অনলাইন
    0.40
     CXCR
    0.39
     যুক্তরাষ্ট্র
    0.39
     ्
    0.39
     ஏற்படும்
    0.39
    internet
    0.39
     Caspian
    0.38
     پ
    0.38
    divide
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.