© 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. 22-GEMMASCOPE-RES-131K
    7. 12463
    Prev
    Next
    INDEX
    Explanations

    reporting speech and specific entities

    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
    calibur
    -0.80
    AddComponent
    -0.79
     
    -0.77
    گز
    -0.76
     mitochondria
    -0.75
    wale
    -0.75
    ?
    -0.74
    さんも
    -0.72
    有些人
    -0.72
    aucune
    -0.71
    POSITIVE LOGITS
     spune
    0.98
    digos
    0.97
     environments
    0.95
    raktion
    0.91
     specifically
    0.90
    ℜ
    0.89
    énier
    0.88
     forbindelse
    0.86
    lable
    0.86
    continence
    0.85
    Activations Density 0.001%

    No Known Activations