© 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. 20595
    Prev
    Next
    INDEX
    Explanations

    organization and finance explanation

    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
     Shawn
    0.38
     dopo
    0.38
    日閲覧
    0.37
    䢔
    0.37
    ̀
    0.36
     サイズ
    0.36
    riamo
    0.36
     腕時計
    0.35
     fateful
    0.35
    )}^
    0.35
    POSITIVE LOGITS
    COMPANY
    0.46
    Company
    0.45
     leakage
    0.42
     کمپنی
    0.42
    شركة
    0.41
    FUND
    0.40
    localhost
    0.39
    company
    0.37
     الشركة
    0.37
     turnkey
    0.37
    Activations Density 0.002%

    No Known Activations