© 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. 60310
    Prev
    Next
    INDEX
    Explanations

    foreign words and emojis

    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
     for
    -1.87
     while
    -1.79
     an
    -1.77
     provide
    -1.72
     as
    -1.67
     before
    -1.66
     these
    -1.65
    ,
    -1.60
     There
    -1.60
     on
    -1.60
    POSITIVE LOGITS
    
    1.88
     multicolore
    1.72
    Manfaat
    1.69
     pantalon
    1.63
     seksi
    1.59
    🫃
    1.59
     camiset
    1.59
     kader
    1.58
     demokra
    1.55
    𓁹
    1.54
    Activations Density 0.119%

    No Known Activations