© 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. 32123
    Prev
    Next
    INDEX
    Explanations

    questions about tensor shape and memory

    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
    acin
    -0.72
    chossen
    -0.71
    LAM
    -0.71
    ghold
    -0.71
     Wednesday
    -0.70
    ernes
    -0.70
    ourced
    -0.70
    fromUtf
    -0.70
     DRIVE
    -0.69
     ră
    -0.68
    POSITIVE LOGITS
     memory
    1.05
     dims
    0.88
    layout
    0.84
     Memory
    0.82
     pitches
    0.80
    布団
    0.79
    memory
    0.79
     dim
    0.78
    Pitch
    0.78
     Shape
    0.77
    Activations Density 0.010%

    No Known Activations