© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 7970
    Prev
    Next
    INDEX
    Explanations

    connecting segments

    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_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    㖑
    0.42
     insecurity
    0.39
    เชสเตอร์
    0.39
     valores
    0.38
    फ्तार
    0.38
    相談
    0.38
     asymmetries
    0.38
    λεσμα
    0.38
    ̗
    0.37
    პერ
    0.37
    POSITIVE LOGITS
     AB
    0.70
    连接
    0.70
     connecting
    0.67
    connecting
    0.59
     segment
    0.59
     连接
    0.58
     Segment
    0.57
     Connecting
    0.57
    連接
    0.57
     segmento
    0.56
    Activations Density 0.195%

    No Known Activations