© 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. 34-GEMMASCOPE-RES-131K
    7. 63616
    Prev
    Next
    INDEX
    Explanations

    numerical currency values

    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_34/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
     millions
    -1.41
     millones
    -1.18
    Millions
    -1.14
     milioni
    -1.10
     Millions
    -1.08
     million
    -1.08
    million
    -1.07
    millions
    -1.05
     miljoen
    -1.05
    Million
    -1.05
    POSITIVE LOGITS
     flera
    1.09
     vários
    0.92
    ől
    0.91
    Dermal
    0.83
    三千
    0.80
    Meto
    0.79
    ਥ
    0.78
     ſeveral
    0.77
     نا
    0.77
    Deja
    0.76
    Activations Density 0.074%

    No Known Activations