© 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. 34-GEMMASCOPE-RES-131K
    4. 84881
    Prev
    Next
    INDEX
    Explanations

    semicolons followed by imports

    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
    Према
    -0.90
     molecules
    -0.85
    them
    -0.85
    Τ
    -0.82
     człowiek
    -0.82
     spaces
    -0.82
     someone
    -0.81
    是一種
    -0.81
    According
    -0.81
     mechanisms
    -0.81
    POSITIVE LOGITS
     rũ
    0.91
    + 
    0.84
     guerres
    0.80
    itecture
    0.80
     booty
    0.77
    óval
    0.77
     verstor
    0.76
     ETL
    0.74
     leçons
    0.74
    meu
    0.73
    Activations Density 0.031%

    No Known Activations