© 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. 91352
    Prev
    Next
    INDEX
    Explanations

    declare or disclose information

    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
    ECO
    -0.93
     barne
    -0.92
    质量
    -0.78
    eco
    -0.78
    哌
    -0.73
    ılması
    -0.73
    站点
    -0.73
     Mapp
    -0.71
     Eco
    -0.70
    ᱲ
    -0.69
    POSITIVE LOGITS
     declaration
    1.05
     declare
    1.04
     declarations
    0.98
    declaration
    0.97
    declare
    0.95
    Declaration
    0.89
     disclosures
    0.89
     Serving
    0.86
     serving
    0.85
    serving
    0.85
    Activations Density 0.012%

    No Known Activations