© 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. 50068
    Prev
    Next
    INDEX
    Explanations

    compound proper 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_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
     réve
    -1.63
     energii
    -1.56
    
    -1.54
     accepte
    -1.52
    殽
    -1.51
     remé
    -1.50
    傒
    -1.46
     dát
    -1.45
     serpiente
    -1.43
    ཥ
    -1.43
    POSITIVE LOGITS
    💓
    1.47
     as
    1.45
     in
    1.45
    🤙
    1.45
    🤘
    1.43
     when
    1.38
    😤
    1.32
    🤪
    1.32
     While
    1.31
    🤤
    1.31
    Activations Density 0.162%

    No Known Activations