© 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. 115815
    Prev
    Next
    INDEX
    Explanations

    vector notation and physics 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
     magnitude
    -1.06
    Magnitude
    -1.05
     Magnitude
    -0.92
    scalar
    -0.89
     scalar
    -0.88
    component
    -0.83
    COMPONENT
    -0.82
     Component
    -0.82
    magnitude
    -0.79
     component
    -0.77
    POSITIVE LOGITS
     velocity
    1.22
    velocity
    1.01
    Velocity
    0.89
     Velocity
    0.88
     vectors
    0.87
    myArray
    0.80
    relenting
    0.76
    grad
    0.75
    lasia
    0.75
     vector
    0.74
    Activations Density 0.020%

    No Known Activations