© 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. 39947
    Prev
    Next
    INDEX
    Explanations

    package/library prefixes

    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
     on
    -1.71
     in
    -1.60
     asfalto
    -1.59
    garis
    -1.48
     from
    -1.48
     évé
    -1.48
    pente
    -1.47
    bahar
    -1.47
     balón
    -1.46
    pasti
    -1.45
    POSITIVE LOGITS
    u
    2.16
    is
    2.03
    im
    1.97
    p
    1.94
    f
    1.91
    ar
    1.88
    l
    1.87
    b
    1.84
    r
    1.80
    k
    1.78
    Activations Density 0.017%

    No Known Activations