© 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. 65009
    Prev
    Next
    INDEX
    Explanations

    financial or technical terms

    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
    堝
    0.45
    分别
    0.45
    鎊
    0.43
    において
    0.42
    銀行
    0.42
    aia
    0.42
    这样
    0.42
    fted
    0.41
    ittäin
    0.41
    <0x19>
    0.41
    POSITIVE LOGITS
     връ
    0.42
     cheerful
    0.42
     pero
    0.41
     gilt
    0.41
     değil
    0.41
     gars
    0.40
     choking
    0.39
    неш
    0.38
     immunity
    0.38
     camisa
    0.38
    Activations Density 0.001%

    No Known Activations