© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54434
    Prev
    Next
    INDEX
    Explanations

    brand and company names

    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
     ombro
    -1.51
     blusas
    -1.48
     conster
    -1.48
     procra
    -1.47
    簠
    -1.44
     kemer
    -1.42
     feltro
    -1.41
     lanterna
    -1.41
    搋
    -1.37
     frustra
    -1.36
    POSITIVE LOGITS
    x
    1.70
    b
    1.67
    Q
    1.64
    f
    1.62
    l
    1.55
    C
    1.54
    X
    1.52
    j
    1.51
    am
    1.50
    P
    1.50
    Activations Density 0.080%

    No Known Activations