© 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. 39272
    Prev
    Next
    INDEX
    Explanations

    job flow"}, "uintptr_t"}, "Lucha Libre"}

    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
    riera
    -0.89
     provide
    -0.89
    HXLINE
    -0.87
    тыми
    -0.87
     нейтра
    -0.84
     still
    -0.83
    ără
    -0.83
     immediately
    -0.83
    Liefer
    -0.82
     localVar
    -0.81
    POSITIVE LOGITS
    knows
    0.91
    腭
    0.88
     جميع
    0.85
     hé
    0.83
     élev
    0.83
     anciens
    0.80
     aufgebaut
    0.80
    哪个
    0.79
    لاین
    0.79
     guz
    0.79
    Activations Density 0.050%

    No Known Activations