© 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. 12404
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and identifiers

    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
    y
    -1.79
    T
    -1.73
    j
    -1.72
    r
    -1.70
    al
    -1.65
     of
    -1.63
    w
    -1.62
     T
    -1.59
     R
    -1.59
    g
    -1.59
    POSITIVE LOGITS
    Reak
    1.75
    zdo
    1.63
    Penjelasan
    1.59
    Kamera
    1.57
    Makan
    1.56
     remercier
    1.56
    adakan
    1.55
    Warna
    1.55
     salonu
    1.54
     horaire
    1.54
    Activations Density 0.003%

    No Known Activations