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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110652
    Prev
    Next
    INDEX
    Explanations

    factor analysis and related methods

    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
     precis
    -0.74
     estancia
    -0.73
    learn
    -0.72
     clinch
    -0.70
    arela
    -0.68
     dea
    -0.67
    Assembler
    -0.67
     nét
    -0.66
     Gn
    -0.66
    assembler
    -0.66
    POSITIVE LOGITS
     rotated
    1.53
     rotation
    1.34
     rotate
    1.32
     factoring
    1.27
    Rotate
    1.27
    rotated
    1.25
     loading
    1.23
     Rotation
    1.21
     factor
    1.20
     extraction
    1.19
    Activations Density 0.029%

    No Known Activations