© 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. 11281
    Prev
    Next
    INDEX
    Explanations

    Appellate Division, Second Department

    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
    其他的
    -0.93
    дизайн
    -0.89
    还挺
    -0.89
    сылка
    -0.88
    stützung
    -0.87
    其余
    -0.87
     Cebu
    -0.86
    楣
    -0.85
    还是很
    -0.85
    Bjs
    -0.85
    POSITIVE LOGITS
    ůže
    0.92
     psz
    0.92
     Cæ
    0.91
     Bahkan
    0.90
     Enkel
    0.87
     cammino
    0.87
    ensaft
    0.86
     newInstance
    0.84
     суток
    0.84
    ор
    0.84
    Activations Density 0.000%

    No Known Activations