© 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. 231971
    Prev
    Next
    INDEX
    Explanations

    productiviy, data, spectral

    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
    🧩
    0.55
    durationType
    0.52
     प्लांट्स
    0.50
    EQU
    0.50
    കു
    0.50
    湪
    0.48
     विद्यार्थियों
    0.47
     প্রতিনিধ
    0.47
    াহতি
    0.47
    뛴
    0.47
    POSITIVE LOGITS
     Table
    0.54
    ↵
    0.52
    2
    0.50
     جدول
    0.50
     tens
    0.48
     Tens
    0.47
    spectra
    0.45
     Lind
    0.44
     Data
    0.44
     spectral
    0.44
    Activations Density 0.003%

    No Known Activations