© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 84010
    Prev
    Next
    INDEX
    Explanations

    book publisher names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sales
    0.40
    PRINT
    0.40
     एमबी
    0.38
     Изда
    0.37
    క
    0.37
     Printing
    0.37
    lished
    0.36
    asc
    0.36
    쌈
    0.36
     изда
    0.36
    POSITIVE LOGITS
     itth
    0.41
     poursuit
    0.40
     noncommutative
    0.40
    ಜ್ಞ
    0.39
    पछि
    0.38
     spectator
    0.37
    avacak
    0.37
     reboot
    0.37
     costumbres
    0.37
     উপযোগী
    0.37
    Activations Density 0.001%

    No Known Activations