© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108027
    Prev
    Next
    INDEX
    Explanations

    numbers followed by sections

    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
    ineri
    -0.95
     heilig
    -0.82
    toplasm
    -0.81
    cerely
    -0.79
    ENARIO
    -0.79
    bilecek
    -0.76
    댕
    -0.76
     description
    -0.76
    jeremy
    -0.76
     desirable
    -0.75
    POSITIVE LOGITS
     sections
    2.27
     section
    2.19
     chapters
    1.75
     chapter
    1.52
     secciones
    1.38
     parts
    1.28
     pages
    1.25
    sections
    1.23
     bagian
    1.23
     part
    1.22
    Activations Density 0.044%

    No Known Activations