© 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. 62509
    Prev
    Next
    INDEX
    Explanations

    stock market and executive dysfunction

    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
    校
    -0.83
    elux
    -0.82
     тру
    -0.81
     dota
    -0.80
     التش
    -0.79
    խ
    -0.78
    artments
    -0.77
    Intellectual
    -0.77
     мі
    -0.75
     Logan
    -0.75
    POSITIVE LOGITS
     Brokers
    1.13
     brokers
    1.06
     floor
    0.96
     broker
    0.92
     speculative
    0.91
     Parkplatz
    0.86
     dealings
    0.84
     valeurs
    0.84
     speculation
    0.83
    brokers
    0.82
    Activations Density 0.034%

    No Known Activations