© 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. 200026
    Prev
    Next
    INDEX
    Explanations

    news and information sources

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

    testing boundaries or capabilities

    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
    寜
    0.47
     ছুরি
    0.46
    BSDataType
    0.45
     সজ্জিত
    0.44
     Pedagog
    0.44
     некоторое
    0.44
     оборудование
    0.43
     Hochzeit
    0.43
     Educator
    0.42
     โรง
    0.42
    POSITIVE LOGITS
     guilt
    0.51
     affordability
    0.49
     endorph
    0.49
    써
    0.47
     migraines
    0.47
    ਗ
    0.47
     allergens
    0.45
     injustices
    0.45
    िश्व
    0.45
     obsol
    0.45
    Activations Density 0.001%

    No Known Activations