© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110957
    Prev
    Next
    INDEX
    Explanations

    scoundrel

    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
    ᖕ
    0.45
     Neend
    0.43
    OND
    0.42
    盲
    0.40
     CURLE
    0.39
    ర్‌
    0.38
     blindness
    0.38
    AuthProvider
    0.37
     virus
    0.37
    Authority
    0.37
    POSITIVE LOGITS
     instal
    0.43
    押
    0.41
    គ្រប់
    0.40
     হত
    0.39
     science
    0.38
     Install
    0.38
    取材
    0.38
    ishy
    0.38
     install
    0.38
    gee
    0.38
    Activations Density 0.001%

    No Known Activations