© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45490
    Prev
    Next
    INDEX
    Explanations

    variable assignment or concatenation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    不但
    -1.58
    ฀
    -1.58
     Improves
    -1.52
    eſ
    -1.52
     momentous
    -1.50
     focuses
    -1.48
     prieten
    -1.48
     Promotes
    -1.44
    ）、
    -1.43
     specif
    -1.40
    POSITIVE LOGITS
    Some
    2.06
     when
    2.03
     for
    2.02
     only
    1.98
     like
    1.98
     if
    1.95
    when
    1.91
     as
    1.77
    When
    1.75
     Some
    1.72
    Activations Density 0.055%

    No Known Activations