© 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. 21521
    Prev
    Next
    INDEX
    Explanations

    prices and monetary 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_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
     mesmerizing
    -1.78
     göm
    -1.77
    </sub>
    -1.74
     ambassade
    -1.74
    feer
    -1.70
    ዬ
    -1.69
     granja
    -1.64
     elbise
    -1.64
     estadia
    -1.64
     Signalez
    -1.63
    POSITIVE LOGITS
     because
    1.92
     в
    1.86
    ↵↵
    1.83
    when
    1.66
    er
    1.63
    Our
    1.62
    In
    1.59
    When
    1.54
     from
    1.51
    From
    1.51
    Activations Density 0.105%

    No Known Activations