© 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. 119834
    Prev
    Next
    INDEX
    Explanations

    pieces per design

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

    most presented accepted

    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
     Viking
    0.44
     Partnership
    0.43
    髖
    0.43
     Swinging
    0.43
    承包人
    0.42
     संध्या
    0.40
     लोकल
    0.40
    ranged
    0.39
    Underv
    0.39
    Radial
    0.39
    POSITIVE LOGITS
     சூ
    0.47
     بين
    0.43
     [(
    0.42
    ("(
    0.41
     nhân
    0.41
     biznes
    0.41
     soy
    0.40
     přij
    0.40
    apos
    0.39
     eşit
    0.39
    Activations Density 0.000%

    No Known Activations