© 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. 31-GEMMASCOPE-2-RES-262K
    7. 9610
    Prev
    Next
    INDEX
    Explanations

    indicator variables and series

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     berkel
    0.44
     userName
    0.41
    創作
    0.40
    两人
    0.40
     continuamente
    0.40
    如今
    0.39
    肉
    0.39
     relieved
    0.39
     shayari
    0.38
    
    0.38
    POSITIVE LOGITS
     Applied
    0.44
    zeta
    0.43
    Fra
    0.42
    Swiss
    0.42
    Applied
    0.40
    シャ
    0.39
    ζ
    0.39
    Pro
    0.38
     Applic
    0.38
    Applic
    0.38
    Activations Density 0.000%

    No Known Activations