© 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. 60480
    Prev
    Next
    INDEX
    Explanations

    vector and matrix operations

    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
     Bridgewater
    -0.84
     Jars
    -0.79
     paraphrase
    -0.74
    Stayed
    -0.74
     橋
    -0.73
     Chaucer
    -0.72
     Venta
    -0.70
    Chau
    -0.69
     إس
    -0.69
     retrospect
    -0.69
    POSITIVE LOGITS
     vector
    1.95
    vector
    1.56
     vectors
    1.55
     matrix
    1.51
     matrices
    1.29
     Vector
    1.28
    disp
    1.20
     vectores
    1.17
    vectors
    1.17
     vecteur
    1.15
    Activations Density 0.039%

    No Known Activations