© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11992
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun mine

    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
     you
    -2.63
     of
    -2.52
     it
    -2.39
     in
    -2.31
    zegovina
    -2.17
    ,'
    -2.09
     by
    -2.03
    鴣
    -1.96
     kullanılan
    -1.91
    izational
    -1.87
    POSITIVE LOGITS
    鸲
    2.28
    䛗
    2.22
    The
    2.20
    </h3>
    2.16
    %;
    
    2.13
    o
    2.06
     основе
    2.05
    u
    2.02
    EdgeInsets
    1.99
    perhaps
    1.98
    Activations Density 0.004%

    No Known Activations