© 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. 22-GEMMASCOPE-RES-131K
    4. 12886
    Prev
    Next
    INDEX
    Explanations

    rock formations and geological features

    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_22/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
    ּוֹ
    -1.50
     choices
    -1.47
     options
    -1.47
     then
    -1.45
     cost
    -1.41
     option
    -1.40
     choice
    -1.39
     бампер
    -1.37
     оружи
    -1.35
     παι
    -1.34
    POSITIVE LOGITS
    ׇ
    2.19
     ویتامین
    2.08
    อร่อย
    1.87
     النبات
    1.71
     princesas
    1.58
    ֳ
    1.55
    När
    1.38
     colch
    1.38
     mercredi
    1.36
     włosów
    1.36
    Activations Density 0.041%

    No Known Activations