© 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. 44568
    Prev
    Next
    INDEX
    Explanations

    currency pairs, indices, gold

    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
    ⽼
    -1.49
     They
    -1.45
     your
    -1.43
     they
    -1.43
     vedo
    -1.37
     家具
    -1.30
    킁
    -1.30
    Also
    -1.29
     menengah
    -1.29
     custodia
    -1.28
    POSITIVE LOGITS
    Dalam
    1.30
    諍
    1.24
     abbreviation
    1.17
    dungen
    1.14
    אם
    1.13
     MAYO
    1.13
    Aunque
    1.13
    adidas
    1.12
    uminum
    1.11
     totals
    1.11
    Activations Density 0.023%

    No Known Activations