© 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. 10869
    Prev
    Next
    INDEX
    Explanations

    Crimea

    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
    و
    0.45
    doFilter
    0.43
     MR
    0.43
    不同的
    0.42
     temperatures
    0.42
     MRI
    0.41
    模板
    0.41
     bois
    0.41
    วง
    0.41
    را
    0.41
    POSITIVE LOGITS
     других
    0.52
     замети
    0.50
     忄
    0.49
     devoured
    0.48
    🖐
    0.47
     Анали
    0.47
    䍧
    0.47
     сезона
    0.47
     оде
    0.47
     〢
    0.47
    Activations Density 0.004%

    No Known Activations