© 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. 229649
    Prev
    Next
    INDEX
    Explanations

    his outsider, to be, intend to

    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
    ari
    0.54
    UN
    0.47
    Ref
    0.45
    Method
    0.45
    riet
    0.43
    Ar
    0.43
    Mj
    0.43
    um
    0.41
     услу
    0.41
    _
    0.41
    POSITIVE LOGITS
     bisc
    0.50
     Nhật
    0.49
     Vive
    0.48
     Gink
    0.48
     lòng
    0.48
     tròn
    0.48
     móvil
    0.47
     muối
    0.47
     nhựa
    0.47
     hatching
    0.46
    Activations Density 0.000%

    No Known Activations