© 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. 80786
    Prev
    Next
    INDEX
    Explanations

    beneath

    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
    e
    -3.28
    на
    -2.88
    li
    -2.88
    ed
    -2.80
    an
    -2.63
     wrest
    -2.58
    si
    -2.56
    سبة
    -2.45
     Currently
    -2.42
    栩
    -2.38
    POSITIVE LOGITS
     メニュー
    2.53
    咴
    2.42
    vantaged
    2.42
    乄
    2.41
     disfruta
    2.31
    ↵
    2.28
    licitud
    2.27
    archiwizowane
    2.25
    s
    2.22
    襯
    2.22
    Activations Density 0.003%

    No Known Activations