© 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. 16479
    Prev
    Next
    INDEX
    Explanations

    sports official terminology

    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
    Not in Any Lists

    No Comments

    Negative Logits
     \
    -1.69
     '
    -1.31
    d
    -1.27
    \
    -1.26
     '';
    -1.24
    不大
    -1.23
    就可以
    -1.17
    =
    -1.16
     $
    -1.13
    věr
    -1.11
    POSITIVE LOGITS
    "¿
    1.41
     huur
    1.28
     WIFE
    1.28
    蜮
    1.26
     apparence
    1.25
    📢
    1.22
    ㈯
    1.21
    鹟
    1.20
     ſuch
    1.20
     复古
    1.20
    Activations Density 0.016%

    No Known Activations