© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93943
    Prev
    Next
    INDEX
    Explanations

    mathematical transformations and matrices

    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
    Mail
    -0.80
     syk
    -0.75
     مركز
    -0.73
     interak
    -0.73
    бурге
    -0.72
     resistivity
    -0.70
    uesia
    -0.69
    medaille
    -0.69
     Jalisco
    -0.68
     fem
    -0.68
    POSITIVE LOGITS
     transformation
    1.27
     rotation
    1.15
     change
    1.08
     Transformation
    1.07
    transformation
    1.03
    Transformation
    0.97
    rotation
    0.95
     rotations
    0.93
    Rotation
    0.92
     orthogonal
    0.91
    Activations Density 0.023%

    No Known Activations