© 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. 102730
    Prev
    Next
    INDEX
    Explanations

    concluding phase or event

    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
    JIT
    -0.87
     अन्य
    -0.82
    -0.79
     Даль
    -0.77
    osc
    -0.75
     бел
    -0.75
    nière
    -0.74
    actual
    -0.74
     椅子
    -0.74
     MainActivity
    -0.73
    POSITIVE LOGITS
     finally
    5.03
    finally
    3.94
    Finally
    3.86
     Finally
    3.70
     finalmente
    3.52
     наконец
    3.33
     enfin
    2.89
     Finalmente
    2.73
    Finalmente
    2.67
     FINALLY
    2.58
    Activations Density 0.011%

    No Known Activations