© 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. 59301
    Prev
    Next
    INDEX
    Explanations

    imagining and visualizing

    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
    یکا
    -0.96
    号
    -0.85
    showMessage
    -0.85
    гово
    -0.84
     Indicates
    -0.83
    ּוֹ
    -0.82
     initialization
    -0.80
     mê
    -0.80
    веде
    -0.80
     замети
    -0.80
    POSITIVE LOGITS
     imagining
    3.72
     imagine
    3.48
     envision
    3.30
     imagined
    3.28
     imagines
    3.05
     picture
    2.89
     image
    2.78
     imagination
    2.77
     visualize
    2.72
     visualization
    2.70
    Activations Density 0.051%

    No Known Activations