© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12145
    Prev
    Next
    INDEX
    Explanations

    `the` followed by specific nouns

    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
     nuov
    -1.51
     gewi
    -1.48
     spesifik
    -1.45
     menyen
    -1.45
    Instead
    -1.42
     quoc
    -1.39
     elefante
    -1.38
     harap
    -1.38
    Fonction
    -1.38
     pengar
    -1.38
    POSITIVE LOGITS
     not
    1.85
     Every
    1.69
     Even
    1.58
     Often
    1.54
     During
    1.52
     Surprisingly
    1.51
     Getting
    1.50
     exuberant
    1.49
     F
    1.49
     As
    1.48
    Activations Density 0.086%

    No Known Activations