Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 64841
    Prev
    Next
    INDEX
    Explanations

    code block enders

    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_65k_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
     Fake
    0.41
    h
    0.41
    p
    0.39
    l
    0.38
    ani
    0.38
    null
    0.38
     [];
    0.37
     حروف
    0.37
    4
    0.36
    rana
    0.36
    POSITIVE LOGITS
     wets
    0.46
    ट्रोल
    0.42
     मदत
    0.40
     pricey
    0.40
    が良い
    0.39
     يصل
    0.39
     পতিত
    0.38
     koristiti
    0.38
     தடை
    0.38
    鮎
    0.38
    Activations Density 0.006%

    No Known Activations