© 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. 9841
    Prev
    Next
    INDEX
    Explanations

    logical operations and true/false

    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
     of
    -1.64
     this
    -1.12
    group
    -0.93
     har
    -0.89
    With
    -0.88
    STOT
    -0.86
    It
    -0.86
    Not
    -0.85
     to
    -0.85
    》。
    -0.84
    POSITIVE LOGITS
     verschillende
    1.02
     konkrét
    1.02
     échange
    1.02
     olika
    1.02
     aprobado
    1.00
    
    1.00
    elum
    0.98
     légère
    0.98
     různých
    0.98
     verschil
    0.97
    Activations Density 0.015%

    No Known Activations