© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84700
    Prev
    Next
    INDEX
    Explanations

    Notable people and their professions

    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
    französ
    -0.95
     categorias
    -0.90
     vivía
    -0.82
    čit
    -0.81
    <%@
    -0.79
     смарт
    -0.77
    проек
    -0.77
    ент
    -0.77
     colegas
    -0.76
    ėjimas
    -0.73
    POSITIVE LOGITS
     actors
    1.57
     actor
    1.38
     athletes
    1.20
     actress
    1.20
     actresses
    1.15
     politicians
    1.12
     literary
    1.10
     musicians
    1.08
     astronaut
    1.06
     composer
    1.05
    Activations Density 0.069%

    No Known Activations