© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 152782
    Prev
    Next
    INDEX
    Explanations

    organizational, medical, and descriptive contexts

    np_acts-logits-general · gemini-2.5-flash-lite

    focus on physical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    分配
    0.44
    庿
    0.40
    0
    0.39
    Allocation
    0.38
     আগামীকাল
    0.38
    μ
    0.38
    音
    0.38
    με
    0.38
    mid
    0.38
    K
    0.38
    POSITIVE LOGITS
    UGUST
    0.52
     contradictions
    0.50
     ensued
    0.49
     เหรอ
    0.47
     estando
    0.47
     contradicting
    0.46
     सत्ता
    0.46
     аж
    0.46
     ವರ್ಷ
    0.46
     وصلنا
    0.45
    Activations Density 0.001%

    No Known Activations