© 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. 29060
    Prev
    Next
    INDEX
    Explanations

    000, 001, 002, 003

    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
    '
    -2.14
    全都
    -1.78
    哢
    -1.68
     actúa
    -1.59
     ganzes
    -1.54
    ensão
    -1.52
     Then
    -1.51
     注
    -1.42
     bele
    -1.41
    翆
    -1.40
    POSITIVE LOGITS
     який
    1.70
    ’
    1.57
    izacji
    1.52
    僕は
    1.50
     vindt
    1.49
     години
    1.48
    анна
    1.48
    isation
    1.47
    〜。
    1.47
     of
    1.45
    Activations Density 0.036%

    No Known Activations