© 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. 90911
    Prev
    Next
    INDEX
    Explanations

    degree, manual, performed, available

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

    single File

    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
     Gossip
    0.50
    定義
    0.49
    备案
    0.48
    ค์
    0.48
    Editors
    0.48
     edi
    0.48
    UNT
    0.48
     Tristan
    0.47
    煕
    0.46
    羲
    0.46
    POSITIVE LOGITS
     большей
    0.48
     possessions
    0.46
    ي
    0.45
     preserved
    0.44
     drained
    0.44
    طي
    0.43
     dampened
    0.42
     قي
    0.42
     extinguished
    0.42
    رش
    0.42
    Activations Density 0.000%

    No Known Activations