© 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. 22-GEMMASCOPE-RES-131K
    7. 39922
    Prev
    Next
    INDEX
    Explanations

    final step

    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_22/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
    XDECREF
    -0.94
    octubre
    -0.91
    ául
    -0.89
     tripled
    -0.89
     fría
    -0.86
    Firstly
    -0.86
     eenvou
    -0.85
     firstly
    -0.84
    itada
    -0.84
    从未
    -0.84
    POSITIVE LOGITS
     then
    1.58
     finally
    1.32
    最后
    1.14
     final
    1.13
     ended
    1.05
     terminate
    1.02
    สร
    1.00
     cuối
    1.00
     eventually
    0.98
     ends
    0.95
    Activations Density 0.011%

    No Known Activations