© 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. 83358
    Prev
    Next
    INDEX
    Explanations

    the followed by a noun

    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
     sesuatu
    -1.19
     зробити
    -1.16
     turísticos
    -1.03
     disfrute
    -1.03
    卨
    -1.02
    šče
    -1.00
     naturaleza
    -0.99
     velmi
    -0.98
    蘋
    -0.98
     gastronomía
    -0.97
    POSITIVE LOGITS
     help
    3.34
     exception
    2.33
     aid
    2.30
     assistance
    2.02
     aim
    2.02
     intention
    2.00
     same
    1.92
    help
    1.88
     added
    1.82
     addition
    1.79
    Activations Density 0.054%

    No Known Activations