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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43516
    Prev
    Next
    INDEX
    Explanations

    control commands and actions

    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_31_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
     artificially
    0.42
    Induced
    0.41
    ਨ
    0.40
    asyonu
    0.40
    ᆹ
    0.40
     spokesperson
    0.39
     infinitely
    0.39
    ensitive
    0.38
     engross
    0.38
    一项
    0.38
    POSITIVE LOGITS
    money
    0.48
    l
    0.47
    books
    0.46
     Aloha
    0.46
     money
    0.45
     dinero
    0.44
     MONEY
    0.43
     ဒီ
    0.43
     libros
    0.43
     cualquiera
    0.42
    Activations Density 0.000%

    No Known Activations