© 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. 99132
    Prev
    Next
    INDEX
    Explanations

    love success great

    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
     Beamten
    -1.66
     freilich
    -1.52
     deswegen
    -1.49
     by
    -1.48
     Then
    -1.46
    를
    -1.46
     ardından
    -1.45
     dezelfde
    -1.44
     сегодняш
    -1.41
     damal
    -1.41
    POSITIVE LOGITS
    狁
    1.82
    他们
    1.58
    they
    1.55
    琑
    1.54
     the
    1.47
     leiden
    1.46
    вні
    1.42
    their
    1.38
    aneity
    1.35
    mability
    1.34
    Activations Density 0.013%

    No Known Activations