© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54207
    Prev
    Next
    INDEX
    Explanations

    business and financial markets

    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
     recente
    -0.93
     chon
    -0.93
     tuin
    -0.89
     angek
    -0.87
    νος
    -0.84
     rarement
    -0.84
    Vista
    -0.83
    vinced
    -0.83
    ňuje
    -0.82
    zitter
    -0.82
    POSITIVE LOGITS
     new
    1.20
     as
    1.18
     their
    1.05
     get
    1.05
     increased
    0.98
     options
    0.96
     for
    0.96
     now
    0.96
     business
    0.95
     future
    0.93
    Activations Density 0.050%

    No Known Activations