© 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. 149478
    Prev
    Next
    INDEX
    Explanations

    sponsored by or affiliated with

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

    code and documentation

    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
    妽
    0.48
    ajā
    0.46
    俻
    0.45
    Facilities
    0.44
     وړیا
    0.43
     জনসংখ্যার
    0.43
     ז
    0.42
    㬹
    0.42
    alarm
    0.42
     শহরে
    0.42
    POSITIVE LOGITS
     catheters
    0.47
     mucous
    0.45
     foment
    0.45
     самим
    0.43
     aggrav
    0.43
     mismos
    0.42
    ’.
    0.42
     mouthpiece
    0.42
     accomplishes
    0.42
     mesma
    0.42
    Activations Density 0.003%

    No Known Activations