© 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. 34-GEMMASCOPE-RES-131K
    7. 76987
    Prev
    Next
    INDEX
    Explanations

    mathematical and physical concepts

    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
     Feynman
    -0.75
    Metric
    -0.73
    Lut
    -0.73
    iencing
    -0.71
     Metric
    -0.71
    renar
    -0.69
    imetric
    -0.69
     реали
    -0.69
    peter
    -0.68
     DFA
    -0.68
    POSITIVE LOGITS
    पाद
    0.72
    監視
    0.68
     lapse
    0.67
     Poznań
    0.66
    bpp
    0.66
     frames
    0.66
     entlang
    0.66
    thora
    0.65
     lunettes
    0.65
     gaz
    0.65
    Activations Density 0.020%

    No Known Activations