© 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. 130858
    Prev
    Next
    INDEX
    Explanations

    left and leftovers

    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
    </b>
    -2.53
    9
    -2.39
    就把
    -2.23
     tomando
    -2.22
     to
    -2.22
    of
    -2.20
     проблемы
    -2.19
     The
    -2.09
    ING
    -2.05
     buscando
    -2.05
    POSITIVE LOGITS
    媖
    2.61
    ᥬ
    2.59
     japoneses
    2.53
     tampaknya
    2.36
     réfugi
    2.31
    箜
    2.28
    replyreport
    2.23
     Esses
    2.22
     romantique
    2.19
    значення
    2.17
    Activations Density 0.006%

    No Known Activations