© 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. 111340
    Prev
    Next
    INDEX
    Explanations

    Q: financial questions

    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
     in
    -2.05
     through
    -1.99
     since
    -1.84
     during
    -1.69
     four
    -1.64
     while
    -1.60
     utilizes
    -1.56
     three
    -1.55
     before
    -1.54
     many
    -1.52
    POSITIVE LOGITS
    Как
    1.63
     craindre
    1.59
     paroi
    1.57
     THOSE
    1.55
     جدید
    1.53
    wiście
    1.44
     juger
    1.43
    ISTAN
    1.41
    反而
    1.40
    ▭
    1.39
    Activations Density 0.001%

    No Known Activations