© 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. 64325
    Prev
    Next
    INDEX
    Explanations

    sh- words relating to shaders, shale, SHI, and names

    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
    確実に
    -1.06
     вижу
    -1.02
     informs
    -1.00
    odha
    -0.98
     motorista
    -0.98
    ItemModel
    -0.94
     zmieni
    -0.93
    cista
    -0.92
    actively
    -0.91
     втра
    -0.91
    POSITIVE LOGITS
     SH
    1.80
     sh
    1.40
    SH
    1.29
     Sh
    1.18
     SHO
    1.13
    '
    1.12
    Sh
    1.09
     gle
    1.05
     シャ
    1.02
    
    1.02
    Activations Density 0.066%

    No Known Activations