© 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. 77445
    Prev
    Next
    INDEX
    Explanations

    matrix perspective

    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
    olí
    -0.78
    ṙ
    -0.77
    zett
    -0.76
     chargeable
    -0.74
    Choosing
    -0.74
     vector
    -0.73
     คร
    -0.73
     Dimensiones
    -0.72
    pex
    -0.71
    ային
    -0.71
    POSITIVE LOGITS
     matrix
    1.31
     matrices
    1.24
     mat
    1.23
     Matrix
    1.09
     Matrices
    1.06
     model
    1.03
     view
    1.02
    矩阵
    0.98
     MATRIX
    0.97
     world
    0.96
    Activations Density 0.007%

    No Known Activations