© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7474
    Prev
    Next
    INDEX
    Explanations

    principles and design philosophy

    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_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
     kebanyakan
    0.43
     macrophages
    0.40
    ارت
    0.39
     clearInterval
    0.39
    癃
    0.39
     hầu
    0.39
    ileges
    0.39
     plaf
    0.38
     maxit
    0.38
    琯
    0.38
    POSITIVE LOGITS
     CAGR
    0.43
    ဉ်
    0.42
    Ｗ
    0.42
    勃
    0.41
    СТЕ
    0.41
    metric
    0.40
    arger
    0.40
    美しい
    0.40
    ATEST
    0.39
    駒
    0.39
    Activations Density 0.003%

    No Known Activations