© 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. 54301
    Prev
    Next
    INDEX
    Explanations

    verb then preposition or adverb

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

    GET requests

    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
    -
    0.49
     alternative
    0.47
     infliction
    0.43
    k
    0.42
    ?-
    0.41
    ői
    0.40
     administering
    0.40
    टे
    0.39
    流行
    0.39
    籮
    0.39
    POSITIVE LOGITS
    ध्यक्ष
    0.50
     সমস্যাবলী
    0.49
    )،
    0.48
    ֑
    0.48
     ব্যাপকভাবে
    0.48
     😏
    0.47
     জানে
    0.47
     আছে
    0.46
     раздел
    0.46
     ಸರ್
    0.46
    Activations Density 0.000%

    No Known Activations