© 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. 55796
    Prev
    Next
    INDEX
    Explanations

    React component declarations

    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
    ándor
    -0.87
    Comunic
    -0.77
    bleau
    -0.77
    жмите
    -0.77
     بینی
    -0.76
    ßten
    -0.75
    hous
    -0.74
    Източници
    -0.73
    íst
    -0.73
     pacemaker
    -0.71
    POSITIVE LOGITS
     yapımı
    0.83
     passés
    0.83
     órgãos
    0.82
     péro
    0.81
     lindas
    0.81
     visibilidad
    0.79
     gyóg
    0.79
     temat
    0.77
    Insee
    0.77
     atos
    0.77
    Activations Density 0.005%

    No Known Activations