© 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. 11586
    Prev
    Next
    INDEX
    Explanations

    concepts with prepositions

    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
    表示
    0.46
     نە
    0.43
    bés
    0.43
    ጂ
    0.40
     سواء
    0.40
    可能な
    0.40
    say
    0.39
    sust
    0.39
    安定
    0.39
    ᴇ
    0.39
    POSITIVE LOGITS
     sambil
    0.60
     melalui
    0.52
     without
    0.50
     through
    0.49
     anhand
    0.49
     whilst
    0.48
     لمدة
    0.46
     tanpa
    0.46
    ผ่าน
    0.46
     using
    0.45
    Activations Density 0.144%

    No Known Activations