© 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. 82324
    Prev
    Next
    INDEX
    Explanations

    declared, designated, recognized

    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
    াঁ
    -0.79
    诟
    -0.79
     asisti
    -0.77
     AssemblyVersion
    -0.73
     finnas
    -0.72
    makeatletter
    -0.71
    isDebugEnabled
    -0.71
    asants
    -0.71
    RequestContext
    -0.70
     своє
    -0.69
    POSITIVE LOGITS
     declared
    3.88
     declare
    3.41
     designated
    3.25
     declaring
    3.03
     declaration
    3.03
     declares
    2.94
     designation
    2.94
    declared
    2.75
     designate
    2.70
    designated
    2.64
    Activations Density 0.093%

    No Known Activations