© 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-65K
    7. 1924
    Prev
    Next
    INDEX
    Explanations

    Fight the New Drug

    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
     TypeScript
    0.29
     Java
    0.27
    使用
    0.24
     stylistic
    0.23
     Machine
    0.23
     AutoML
    0.22
     a
    0.22
     somewhat
    0.21
    Java
    0.21
     XPath
    0.21
    POSITIVE LOGITS
     сайті
    0.25
     website
    0.25
    ина
    0.24
     сайте
    0.24
    ють
    0.23
    и
    0.22
     blogs
    0.21
    ила
    0.21
     WEBSITE
    0.21
     сайт
    0.21
    Activations Density 0.261%

    No Known Activations