© 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. 23910
    Prev
    Next
    INDEX
    Explanations

    scientific lattice structures

    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
    isierung
    -0.80
    strates
    -0.78
    钨
    -0.73
    acijos
    -0.72
    态度
    -0.72
     쿠
    -0.72
    linha
    -0.71
    consciousness
    -0.71
     abger
    -0.71
     루
    -0.71
    POSITIVE LOGITS
     points
    0.94
     site
    0.93
    点
    0.93
    Spacing
    0.90
     SITES
    0.86
    Points
    0.85
    ovac
    0.80
    FEAT
    0.79
     Spacing
    0.79
     Points
    0.78
    Activations Density 0.024%

    No Known Activations