© 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. 104690
    Prev
    Next
    INDEX
    Explanations

    directions, numbers, sale, git

    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
    BufferException
    -0.89
     Palest
    -0.88
     lebe
    -0.87
     tī
    -0.87
     couvert
    -0.87
    netty
    -0.86
     conforto
    -0.85
    ཥ
    -0.84
    mappedBy
    -0.84
    sprzed
    -0.84
    POSITIVE LOGITS
     их
    0.85
    後で
    0.85
    があり
    0.80
    を訪
    0.75
    全ての
    0.73
     incluir
    0.73
     adore
    0.72
     师
    0.69
     المملكة
    0.69
    ม่
    0.68
    Activations Density 0.039%

    No Known Activations