© 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. 40-GEMMASCOPE-2-RES-262K
    7. 30746
    Prev
    Next
    INDEX
    Explanations

    motion and direction

    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_40_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
     windings
    0.45
    普段
    0.43
     resistenza
    0.41
    pertension
    0.39
     <:
    0.39
    曾
    0.39
     организма
    0.39
    காற்று
    0.38
    gravity
    0.38
     fisica
    0.38
    POSITIVE LOGITS
     towards
    0.72
    向
    0.58
     Towards
    0.56
     westward
    0.56
     toward
    0.55
     eastward
    0.55
    Towards
    0.54
     hacia
    0.52
     backwards
    0.52
     steadily
    0.51
    Activations Density 0.012%

    No Known Activations