© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26780
    Prev
    Next
    INDEX
    Explanations

    Custom data labels and charts

    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
     méxico
    -0.94
     není
    -0.92
     bolsas
    -0.91
     aéreo
    -0.91
     cocina
    -0.90
     which
    -0.89
     tém
    -0.89
     deportivas
    -0.88
     acús
    -0.87
    Iš
    -0.85
    POSITIVE LOGITS
    URES
    0.84
     assorted
    0.83
    ทั้งหมด
    0.82
    вица
    0.82
    ivka
    0.82
     полностью
    0.80
     Charlottesville
    0.79
     myriad
    0.79
     angegebenen
    0.79
     sämtliche
    0.78
    Activations Density 0.007%

    No Known Activations