© 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. 47988
    Prev
    Next
    INDEX
    Explanations

    chocolate

    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
    甃
    -2.80
    不是
    -2.61
    ad
    -2.55
    樒
    -2.55
    h
    -2.55
    没有
    -2.53
     большин
    -2.38
    鸰
    -2.34
    á
    -2.33
     vostra
    -2.30
    POSITIVE LOGITS
    .
    2.95
    姈
    2.66
     帅气
    2.63
     Vereinbarung
    2.55
    でしたが
    2.48
    もある
    2.42
     Bedürfn
    2.39
    ”,
    2.38
    龊
    2.38
    zelfde
    2.36
    Activations Density 0.002%

    No Known Activations