© 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. 73548
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with assignments

    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
     was
    -2.02
    </h3>
    -1.98
     may
    -1.89
     is
    -1.89
     '
    -1.84
     there
    -1.74
     does
    -1.73
     has
    -1.72
     would
    -1.65
     first
    -1.63
    POSITIVE LOGITS
    媖
    1.86
    醅
    1.83
    ჻
    1.78
    焢
    1.76
    鳚
    1.73
    〬
    1.71
    feest
    1.69
     akut
    1.65
     banane
    1.65
     paru
    1.62
    Activations Density 0.115%

    No Known Activations