© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    section or Q

    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
    stornos
    -0.77
    ação
    -0.75
    orylation
    -0.74
    キレイ
    -0.73
    these
    -0.73
    riculares
    -0.70
     aument
    -0.69
    ните
    -0.69
     نسخ
    -0.69
    accharide
    -0.69
    POSITIVE LOGITS
     section
    1.53
    section
    1.22
    Section
    1.13
     sections
    1.13
     Section
    1.09
    ection
    0.99
     seção
    0.98
     parallax
    0.94
     разделе
    0.91
     sección
    0.90
    Activations Density 0.009%

    No Known Activations