© 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. 22-GEMMASCOPE-RES-131K
    7. 127864
    Prev
    Next
    INDEX
    Explanations

    UI programming in swift

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     as
    -1.34
     to
    -1.27
     on
    -1.23
     any
    -1.22
    to
    -1.21
     aptly
    -1.21
    G
    -1.20
     which
    -1.10
     from
    -1.09
     only
    -1.07
    POSITIVE LOGITS
    constructed
    1.27
    熥
    1.26
    entieth
    1.24
     réve
    1.22
    requested
    1.20
     poë
    1.19
    scheduled
    1.17
    缡
    1.16
    temporary
    1.16
     prét
    1.15
    Activations Density 0.000%

    No Known Activations