© 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. 103252
    Prev
    Next
    INDEX
    Explanations

    Android layout inflation

    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
     bancada
    -1.05
     imprensa
    -1.02
     batalha
    -0.98
     declaração
    -0.97
     ilustração
    -0.96
     grau
    -0.92
     same
    -0.86
    薮
    -0.86
     atividade
    -0.85
    於是
    -0.85
    POSITIVE LOGITS
     that
    1.20
    XCTAssert
    1.06
    onHide
    0.99
    (((
    0.97
     this
    0.96
     but
    0.96
     ejemplares
    0.94
     objects
    0.94
    Activator
    0.93
    越多
    0.93
    Activations Density 0.002%

    No Known Activations