© 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. 11082
    Prev
    Next
    INDEX
    Explanations

    fail to

    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
    硬盘
    -2.08
    これからの
    -2.06
     zwięks
    -1.90
    美国的
    -1.85
     biblia
    -1.83
    榇
    -1.83
     rozwoju
    -1.82
     víc
    -1.81
    után
    -1.80
    过年
    -1.79
    POSITIVE LOGITS
     I
    2.39
    焄
    1.88
     começaram
    1.83
    t
    1.83
    </b>
    1.80
     This
    1.77
    镡
    1.73
    anyeol
    1.70
    if
    1.63
    If
    1.63
    Activations Density 0.011%

    No Known Activations