© 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. 10-GEMMASCOPE-RES-131K
    7. 48464
    Prev
    Next
    INDEX
    Explanations

    what followed by pronoun/subject

    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_10/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
    嚒
    -1.97
     anadolu
    -1.80
    jahre
    -1.76
    
    -1.76
    bluza
    -1.75
    kurtka
    -1.69
    ⃚
    -1.68
    sieger
    -1.67
    ℍ
    -1.66
    produktion
    -1.64
    POSITIVE LOGITS
     the
    1.89
     is
    1.88
     while
    1.76
    While
    1.59
     they
    1.59
            
    1.59
     Ironically
    1.54
    “
    1.52
     where
    1.52
     two
    1.50
    Activations Density 0.015%

    No Known Activations