© 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. 11998
    Prev
    Next
    INDEX
    Explanations

    ultrasonic technology, NES consoles, Nirvana band

    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
    ..........
    -2.83
    訁
    -2.75
    一旁
    -2.70
    寕
    -2.69
    樒
    -2.67
    縢
    -2.66
    .............
    -2.59
    튿
    -2.59
    ſſen
    -2.59
    ............
    -2.58
    POSITIVE LOGITS
     During
    3.08
     После
    2.72
    for
    2.63
    istä
    2.55
    灕
    2.50
     Following
    2.42
     ولی
    2.42
    琤
    2.42
    ه
    2.41
     After
    2.31
    Activations Density 0.004%

    No Known Activations