© 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. 117850
    Prev
    Next
    INDEX
    Explanations

    numbers and mathematical expressions

    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
    olved
    -0.80
     armazenamento
    -0.79
     escuro
    -0.77
     reconhecimento
    -0.73
     doświad
    -0.73
     tepung
    -0.73
     agradável
    -0.72
     impossível
    -0.71
    焦点
    -0.71
     hoped
    -0.70
    POSITIVE LOGITS
    ۡ
    0.84
     Tras
    0.77
    Rejo
    0.73
    Tras
    0.73
     hr
    0.71
     КА
    0.71
    Ӣ
    0.69
    ân
    0.68
     פעם
    0.68
     talent
    0.68
    Activations Density 0.067%

    No Known Activations