© 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. 79148
    Prev
    Next
    INDEX
    Explanations

    mathematical topics and terms

    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
    chende
    -0.85
    herzog
    -0.81
    ору
    -0.79
    addafi
    -0.78
     secrétaire
    -0.78
    Gatt
    -0.78
     Edible
    -0.75
    scriptsize
    -0.74
     cognac
    -0.73
    rapie
    -0.73
    POSITIVE LOGITS
     mathematical
    0.91
     math
    0.90
     математи
    0.84
    maze
    0.81
     mathematics
    0.77
     geometry
    0.76
     algebra
    0.76
     FA
    0.75
     maths
    0.74
    พร
    0.73
    Activations Density 0.004%

    No Known Activations