© 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. 116416
    Prev
    Next
    INDEX
    Explanations

    places and numbers

    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
     Gladstone
    -0.79
     urbana
    -0.71
     sociali
    -0.68
     geleverd
    -0.68
    クタイ
    -0.67
    而来
    -0.67
    нала
    -0.66
    limitations
    -0.66
    hébergement
    -0.65
     belga
    -0.65
    POSITIVE LOGITS
     Rory
    0.78
     Warsaw
    0.77
    вими
    0.77
    ƌ
    0.77
    nible
    0.76
    readFileSync
    0.74
    ńst
    0.73
     Chil
    0.73
    han
    0.73
     Whitley
    0.72
    Activations Density 0.016%

    No Known Activations