© 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. 103776
    Prev
    Next
    INDEX
    Explanations

    adjective of significance

    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
     Einfluß
    -1.01
     möge
    -0.99
     changes
    -0.96
    gemaakt
    -0.96
    ICIA
    -0.95
     прият
    -0.95
    barer
    -0.93
    gruß
    -0.93
    耳边
    -0.92
     pintura
    -0.91
    POSITIVE LOGITS
     significant
    1.27
    ggak
    1.24
    有不少
    1.13
     greater
    1.08
    きれい
    1.05
    Decided
    1.05
     각
    1.01
     major
    0.98
    密切
    0.97
     far
    0.96
    Activations Density 0.116%

    No Known Activations