© 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. 100838
    Prev
    Next
    INDEX
    Explanations

    financial concepts and analysis

    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
     rejet
    -1.34
    又一次
    -1.28
     Inſ
    -1.26
     inden
    -1.19
     was
    -1.17
    INKS
    -1.16
    幼儿园
    -1.16
     discrepan
    -1.13
    今度
    -1.13
    鵙
    -1.12
    POSITIVE LOGITS
     especially
    1.67
     particularly
    1.50
     for
    1.30
     chiefly
    1.26
    越し
    1.24
     their
    1.23
     at
    1.19
     zwłaszcza
    1.17
     typically
    1.16
     stated
    1.15
    Activations Density 0.034%

    No Known Activations