© 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. 103459
    Prev
    Next
    INDEX
    Explanations

    measuring various properties against each other

    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
     morir
    -0.83
     terá
    -0.82
     hoog
    -0.80
     přid
    -0.79
    taku
    -0.78
    ueling
    -0.78
     искусства
    -0.78
    {$\
    -0.78
    ulating
    -0.77
    ℍ
    -0.77
    POSITIVE LOGITS
     versus
    2.88
     vs
    2.55
     as
    2.48
     against
    2.20
    versus
    1.90
     dependence
    1.90
     Versus
    1.84
    Versus
    1.63
    vs
    1.56
     depending
    1.56
    Activations Density 0.081%

    No Known Activations