© 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. 105302
    Prev
    Next
    INDEX
    Explanations

    capitalization, foreign words, proper nouns

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

    data handling and boolean logic

    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
     fehér
    0.51
    পত্রের
    0.50
    BeerItem
    0.50
    storeItem
    0.48
     trộn
    0.48
    员
    0.47
     hosszú
    0.46
     leather
    0.46
    **/
    0.46
    érons
    0.45
    POSITIVE LOGITS
    LIB
    0.45
    Gli
    0.44
     anterior
    0.44
    SOUTH
    0.44
    זה
    0.44
     anuv
    0.44
    Capital
    0.43
     metu
    0.43
    Za
    0.43
    Zag
    0.43
    Activations Density 0.000%

    No Known Activations