© 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. 10-GEMMASCOPE-RES-131K
    7. 118810
    Prev
    Next
    INDEX
    Explanations

    increase in measurable quantities

    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_10/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
    抨
    -1.55
     εκεί
    -1.52
     crux
    -1.51
    R
    -1.48
    mu
    -1.47
    wych
    -1.46
    ('/')
    -1.42
    co
    -1.41
    AAAAA
    -1.40
    </
    -1.37
    POSITIVE LOGITS
     increase
    1.70
    endimiento
    1.52
    赑
    1.43
    orie
    1.41
     its
    1.39
    IZACIÓN
    1.39
    geführten
    1.38
     buscan
    1.38
     помощью
    1.34
    Films
    1.33
    Activations Density 0.272%

    No Known Activations