© 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. 10-GEMMASCOPE-RES-131K
    7. 113402
    Prev
    Next
    INDEX
    Explanations

    financial fund types

    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
     manteiga
    -1.95
    텃
    -1.93
    꿩
    -1.90
    and
    -1.87
     chuckles
    -1.85
     nastro
    -1.77
    毉
    -1.75
     regarde
    -1.68
     keinginan
    -1.67
     nineteen
    -1.66
    POSITIVE LOGITS
     Their
    2.56
    <bos>
    2.03
    になれば
    2.02
     funds
    1.84
    让他们
    1.81
     Therefore
    1.76
     
    1.75
    们的
    1.62
    部は
    1.61
    なのに
    1.60
    Activations Density 0.013%

    No Known Activations