© 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. 94008
    Prev
    Next
    INDEX
    Explanations

    EE or Ee beginnings

    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
    engers
    -0.82
     libri
    -0.81
    vací
    -0.78
    сного
    -0.77
     правый
    -0.77
     enz
    -0.76
     madre
    -0.74
    versible
    -0.74
     cui
    -0.73
     Validity
    -0.73
    POSITIVE LOGITS
     EE
    1.02
    EE
    0.84
    utors
    0.83
    grep
    0.82
    vee
    0.80
     ee
    0.77
    的反
    0.76
     ammat
    0.73
     življen
    0.72
    示意图
    0.72
    Activations Density 0.018%

    No Known Activations