© 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. 8090
    Prev
    Next
    INDEX
    Explanations

    looking 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_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
    何时
    0.37
    емое
    0.36
     नियु
    0.35
     คณิตศาสตร์
    0.34
    igal
    0.34
     कह
    0.33
    Beginning
    0.33
    囗
    0.33
     एल्गोरि
    0.33
     downfall
    0.33
    POSITIVE LOGITS
     intently
    0.68
     towards
    0.66
     directly
    0.64
     sideways
    0.64
     wist
    0.61
     directamente
    0.60
     nervously
    0.60
     upwards
    0.59
     diretamente
    0.56
     toward
    0.55
    Activations Density 0.010%

    No Known Activations