© 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. 34-GEMMASCOPE-RES-131K
    7. 94193
    Prev
    Next
    INDEX
    Explanations

    control systems and operations

    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
    Negative Logits
    dfunding
    -0.94
    зії
    -0.90
    ἵ
    -0.89
    ási
    -0.85
    ropho
    -0.82
    onAttach
    -0.82
    richText
    -0.81
    što
    -0.81
     дом
    -0.80
    締切
    -0.80
    POSITIVE LOGITS
     control
    2.58
     Control
    2.03
    control
    2.03
    Control
    1.94
     monitoring
    1.87
     command
    1.75
     operators
    1.54
     headquarters
    1.52
     operator
    1.51
     operations
    1.47
    Activations Density 0.036%

    No Known Activations