© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 75262
    Prev
    Next
    INDEX
    Explanations

    acquiring skills and prowess

    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
     that
    -2.08
    卨
    -1.35
     trotzdem
    -1.26
    ?
    -1.24
     garçons
    -1.19
    Both
    -1.19
    d
    -1.18
    c
    -1.17
    Y
    -1.17
     viktigt
    -1.16
    POSITIVE LOGITS
    τητα
    1.43
    ített
    1.36
     временем
    1.32
    laient
    1.31
    ことも
    1.30
    情形
    1.29
     ۱۳
    1.29
     antics
    1.28
    ics
    1.27
    尔斯
    1.27
    Activations Density 0.025%

    No Known Activations