© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22348
    Prev
    Next
    INDEX
    Explanations

    sports teams and victories

    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
    Not in Any Lists

    No Comments

    Negative Logits
     it
    -2.05
     as
    -1.52
     их
    -1.48
    As
    -1.43
     had
    -1.38
     because
    -1.38
     their
    -1.38
     its
    -1.33
    It
    -1.30
     and
    -1.23
    POSITIVE LOGITS
    mbgg
    1.32
     vänner
    1.32
    mvh
    1.32
    rachel
    1.31
    ilove
    1.30
    苤
    1.30
     skydd
    1.30
     triko
    1.30
     besonder
    1.29
    整个人
    1.27
    Activations Density 0.095%

    No Known Activations