© 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. 54231
    Prev
    Next
    INDEX
    Explanations

    children's stories and book titles

    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
     metodi
    -0.83
     nutrición
    -0.82
    Kills
    -0.80
     nedir
    -0.79
     gantung
    -0.79
    থা
    -0.78
     pæ
    -0.77
    Tend
    -0.77
     sambil
    -0.76
    ITZER
    -0.76
    POSITIVE LOGITS
    ramientas
    1.08
     Passover
    1.01
     Christmas
    0.95
     adventures
    0.88
    ctivos
    0.87
    máscara
    0.84
     εφ
    0.84
     inventions
    0.83
    artements
    0.83
    諳
    0.82
    Activations Density 0.029%

    No Known Activations