© 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. 34-GEMMASCOPE-RES-131K
    7. 78210
    Prev
    Next
    INDEX
    Explanations

    oriented, focused, driven, centric

    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_34/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
    Экономи
    -0.96
     seres
    -0.93
    ляю
    -0.92
    Vastaa
    -0.91
     beings
    -0.90
    onymy
    -0.88
     vermag
    -0.85
    liato
    -0.85
    Options
    -0.82
     skupina
    -0.82
    POSITIVE LOGITS
     oriented
    3.95
    oriented
    3.28
     orient
    3.05
     Oriented
    3.05
     focused
    2.80
    Oriented
    2.75
    orient
    2.55
     centric
    2.52
     ориенти
    2.42
    focused
    2.38
    Activations Density 0.045%

    No Known Activations