© 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. 12484
    Prev
    Next
    INDEX
    Explanations

    proxy, video ids

    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
     from
    -1.02
    していますが
    -0.94
    nativeElement
    -0.94
     لديك
    -0.93
     всичко
    -0.91
     няколко
    -0.91
    vého
    -0.90
     всички
    -0.90
     verkligen
    -0.88
    もありますが
    -0.87
    POSITIVE LOGITS
     温泉
    0.85
    Corresponding
    0.81
    冷凍
    0.79
    anía
    0.77
     Biologie
    0.76
     dessen
    0.75
     contextLoads
    0.75
     its
    0.75
    ră
    0.74
     increasingly
    0.74
    Activations Density 0.003%

    No Known Activations