© 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. 103763
    Prev
    Next
    INDEX
    Explanations

    numbers and common words

    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
    loroethane
    -0.91
     therefore
    -0.86
    your
    -0.85
     насеље
    -0.84
     your
    -0.83
     naso
    -0.82
    redd
    -0.81
    ͋
    -0.80
     needed
    -0.80
     or
    -0.79
    POSITIVE LOGITS
    Abstract
    1.98
     abstract
    1.48
     Abstract
    1.44
    ▪
    1.31
    ABSTRACT
    1.17
     Publisher
    1.09
    Publisher
    1.02
    ►
    0.99
    Derp
    0.98
    Incluye
    0.98
    Activations Density 0.312%

    No Known Activations