© 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. 36235
    Prev
    Next
    INDEX
    Explanations

    even

    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
    asel
    -1.12
     verschiedenen
    -1.09
     основном
    -1.08
     different
    -1.02
     различни
    -0.98
     behalten
    -0.95
     fällt
    -0.94
    Notae
    -0.92
     немного
    -0.91
    適量
    -0.91
    POSITIVE LOGITS
     even
    2.11
     jopa
    2.09
     навіть
    1.92
    甚至
    1.89
     addirittura
    1.84
     sogar
    1.79
     حتی
    1.77
     nawet
    1.77
     даже
    1.75
     zelfs
    1.74
    Activations Density 0.065%

    No Known Activations