© 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. 103541
    Prev
    Next
    INDEX
    Explanations

    the noun phrase

    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
     biblioteca
    -0.89
    ürt
    -0.88
     exemplo
    -0.86
     squash
    -0.86
     ejemplo
    -0.86
     diferente
    -0.85
     aulas
    -0.85
    hears
    -0.85
    uyer
    -0.85
     dikk
    -0.85
    POSITIVE LOGITS
     woman
    1.73
     victim
    1.41
     owner
    1.39
     women
    1.31
     unnamed
    1.30
     incident
    1.21
     investigation
    1.19
     unidentified
    1.15
     same
    1.10
     male
    1.10
    Activations Density 0.042%

    No Known Activations