© 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. 80805
    Prev
    Next
    INDEX
    Explanations

    Google searches and keywords

    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
     نکنید
    -0.94
    instagram
    -0.93
    avier
    -0.92
    чит
    -0.92
     AssemblyVersion
    -0.90
    ㅓ
    -0.89
    llum
    -0.88
     instagram
    -0.88
     linie
    -0.85
     учета
    -0.85
    POSITIVE LOGITS
     keywords
    1.88
     images
    1.50
     keyword
    1.43
    images
    1.33
     search
    1.20
    关键词
    1.20
    keywords
    1.19
     terms
    1.14
    Images
    1.12
     Images
    1.09
    Activations Density 0.053%

    No Known Activations