© 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. 75487
    Prev
    Next
    INDEX
    Explanations

    advisable, preferable, wise

    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
    杙
    -2.56
     siendo
    -2.48
    )-
    -2.48
    疴
    -2.48
     ilumina
    -2.38
    肫
    -2.36
    徧
    -2.28
    骘
    -2.27
    绺
    -2.17
    ೢ
    -2.17
    POSITIVE LOGITS
    this
    2.94
    4
    2.67
     längere
    2.52
     Someone
    2.45
    g
    2.39
     This
    2.34
     一个
    2.31
     Somebody
    2.28
     Another
    2.27
     одного
    2.25
    Activations Density 0.004%

    No Known Activations