© 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. 122777
    Prev
    Next
    INDEX
    Explanations

    programming frameworks and code execution

    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
    ع
    0.47
    USTOM
    0.45
     dénom
    0.44
     fon
    0.44
     twenties
    0.43
     kans
    0.42
     Chevrolet
    0.41
    edes
    0.40
    p
    0.40
    ۱۹
    0.40
    POSITIVE LOGITS
    ğin
    0.50
    秫
    0.50
     oi
    0.47
    ława
    0.45
     ܀
    0.44
     informó
    0.42
     млн
    0.41
    olics
    0.41
     ছাড়া
    0.40
    DONE
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.