© 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. 55581
    Prev
    Next
    INDEX
    Explanations

    happily ever after

    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
     BytesLike
    -0.80
    heran
    -0.78
    สิทธิ
    -0.75
    キャンプ
    -0.75
    nergie
    -0.74
     undertaken
    -0.73
    cemment
    -0.73
     records
    -0.73
    קר
    -0.73
    emmel
    -0.72
    POSITIVE LOGITS
     happily
    1.27
     lived
    1.15
    lived
    0.99
    happily
    0.98
     live
    0.95
     Happ
    0.91
     happy
    0.89
     lives
    0.88
     lieto
    0.85
    ever
    0.83
    Activations Density 0.009%

    No Known Activations