© 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. 83648
    Prev
    Next
    INDEX
    Explanations

    incorporated, established, successor

    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
     információk
    -0.81
    iapkan
    -0.80
     because
    -0.75
    ʲ
    -0.75
     ואת
    -0.73
     after
    -0.73
    разви
    -0.73
     Unlike
    -0.72
     what
    -0.72
    enes
    -0.70
    POSITIVE LOGITS
    successor
    1.14
     successor
    1.06
    established
    1.03
     seules
    1.00
    opposite
    0.98
     SOLE
    0.97
     Established
    0.97
    Established
    0.96
     successors
    0.95
    corporated
    0.94
    Activations Density 0.027%

    No Known Activations