© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31591
    Prev
    Next
    INDEX
    Explanations

    deferred shading

    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
     Kinshasa
    -0.77
    theilung
    -0.76
     Fing
    -0.75
     тө
    -0.75
    hmigung
    -0.75
    เย
    -0.71
    даря
    -0.69
     Bim
    -0.69
    adays
    -0.69
    uxley
    -0.69
    POSITIVE LOGITS
     exchanger
    1.06
     exchangers
    0.95
     exchange
    0.92
     accommod
    0.88
     like
    0.87
     replacement
    0.85
     exchanges
    0.84
     DST
    0.83
    defer
    0.81
     defer
    0.81
    Activations Density 0.016%

    No Known Activations