© 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. 33679
    Prev
    Next
    INDEX
    Explanations

    code syntax and structure

    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
    曲は
    -0.94
     island
    -0.85
    ッケージ
    -0.84
     masks
    -0.84
     geothermal
    -0.81
     lemn
    -0.77
    ajinan
    -0.75
     connection
    -0.75
     investigar
    -0.75
     nueve
    -0.74
    POSITIVE LOGITS
     Noel
    0.80
    商
    0.79
    rådet
    0.78
    StateManager
    0.73
    ":[
    0.72
    ∥
    0.72
    Noel
    0.71
    setLoading
    0.71
    yyy
    0.70
    ooo
    0.70
    Activations Density 0.014%

    No Known Activations