© 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. 111130
    Prev
    Next
    INDEX
    Explanations

    Nix programming language expressions

    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
     Number
    -0.81
     pandemic
    -0.79
     Dem
    -0.75
    LATIN
    -0.72
     Sav
    -0.71
     Order
    -0.70
    շ
    -0.70
    RegressionTest
    -0.69
    Dem
    -0.69
     Pay
    -0.69
    POSITIVE LOGITS
     Nix
    1.27
     derivation
    1.16
     nix
    1.06
     deriv
    1.05
    deriv
    1.02
    Nix
    1.00
    nix
    0.99
    heure
    0.89
    Attrs
    0.86
    声道
    0.85
    Activations Density 0.033%

    No Known Activations