© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 32868
    Prev
    Next
    INDEX
    Explanations

    code delimiters

    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
    CMAKE
    -0.88
     テープ
    -0.87
     Casinos
    -0.86
     ornate
    -0.85
     Laden
    -0.85
    倏
    -0.84
     contempla
    -0.83
    好きです
    -0.83
    Tema
    -0.82
    lden
    -0.82
    POSITIVE LOGITS
     Basic
    1.23
     Multi
    1.22
     Virtual
    1.13
     Life
    1.06
     Country
    1.04
     Business
    1.02
     Two
    1.02
     Side
    1.00
     Small
    0.98
     Non
    0.98
    Activations Density 0.021%

    No Known Activations