© 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. 12892
    Prev
    Next
    INDEX
    Explanations

    adverbs of frequency or degree

    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
     быть
    0.29
    เป็น
    0.27
    ।
    0.25
    จาก
    0.24
    ใน
    0.24
    으로
    0.23
    ÈRES
    0.23
    在
    0.23
     להיות
    0.23
    取り
    0.22
    POSITIVE LOGITS
    only
    0.26
     hermoso
    0.25
    ിക്കുകയും
    0.25
     asla
    0.23
     only
    0.23
     baik
    0.23
     altijd
    0.22
     mycket
    0.22
    ewalk
    0.22
    也非常
    0.21
    Activations Density 0.187%

    No Known Activations