© 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. 12403
    Prev
    Next
    INDEX
    Explanations

    multiple arguments or variables

    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
    چی
    -1.02
     both
    -1.00
     beiden
    -0.98
     दोनों
    -0.96
     only
    -0.96
     keduanya
    -0.89
    Both
    -0.88
     spørsmål
    -0.88
     angka
    -0.87
    三郎
    -0.86
    POSITIVE LOGITS
     Multiple
    1.01
     múltiples
    1.00
    multiple
    0.99
    ulti
    0.98
     מרו
    0.91
    brtc
    0.89
     cualquier
    0.89
     exceso
    0.89
     Array
    0.88
    但他
    0.88
    Activations Density 0.046%

    No Known Activations