© 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-262K
    7. 3270
    Prev
    Next
    INDEX
    Explanations

    classical or traditional descriptions

    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
     НЕ
    0.47
     όχι
    0.45
     NOT
    0.44
    不仅仅
    0.43
    krét
    0.43
     необы
    0.43
     unconventional
    0.40
    非
    0.40
     YOUR
    0.39
    ไม่ได้
    0.39
    POSITIVE LOGITS
     classica
    0.48
    伝統
    0.42
     tradicion
    0.42
     tradicional
    0.42
     klasik
    0.42
     classic
    0.41
    传统的
    0.41
     tradiz
    0.41
    傳統
    0.41
     klassischen
    0.41
    Activations Density 0.153%

    No Known Activations