© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85952
    Prev
    Next
    INDEX
    Explanations

    company earnings and financial results

    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_10/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
    六年
    -1.76
     meisten
    -1.65
     of
    -1.56
     Eigentü
    -1.48
     in
    -1.46
     would
    -1.38
     You
    -1.35
     Töchter
    -1.30
     représentation
    -1.28
    ズの
    -1.28
    POSITIVE LOGITS
     Frankrijk
    1.73
     ""))
    1.53
     vinyle
    1.45
    糴
    1.44
     illustratie
    1.43
     berge
    1.42
     kimdir
    1.41
     inoxydable
    1.41
          
    1.40
     उन्होंने
    1.38
    Activations Density 0.019%

    No Known Activations