© 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. 22-GEMMASCOPE-RES-131K
    7. 72839
    Prev
    Next
    INDEX
    Explanations

    careers and roles

    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
     it
    -2.22
     new
    -1.90
     this
    -1.86
     that
    -1.82
     their
    -1.59
    仍
    -1.48
     if
    -1.47
     would
    -1.45
     which
    -1.45
     having
    -1.45
    POSITIVE LOGITS
     myös
    1.77
     även
    1.58
    several
    1.49
     uſed
    1.43
     diverses
    1.43
    Život
    1.42
     både
    1.42
     appartement
    1.41
     flera
    1.41
     soupe
    1.38
    Activations Density 0.107%

    No Known Activations