© 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. 53-GEMMASCOPE-2-RES-262K
    7. 1292
    Prev
    Next
    INDEX
    Explanations

    movement to a destination

    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_53_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
    于
    0.52
     στους
    0.49
     terhadap
    0.46
     dedans
    0.46
    於
    0.43
     trong
    0.43
     nisso
    0.42
     wobec
    0.42
     dalam
    0.41
    trong
    0.41
    POSITIVE LOGITS
     إلى
    1.05
    到
    0.97
    ไปยัง
    0.86
     الى
    0.84
     naar
    0.80
     到
    0.79
     to
    0.75
     ወደ
    0.74
    送到
    0.73
     To
    0.71
    Activations Density 0.081%

    No Known Activations