© 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. 130512
    Prev
    Next
    INDEX
    Explanations

    word also

    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
    u
    -2.55
    te
    -2.41
    to
    -2.36
    ti
    -2.28
    8
    -2.22
     they
    -2.02
    c
    -1.95
    e
    -1.88
    k
    -1.88
    tr
    -1.83
    POSITIVE LOGITS
    ियम
    1.66
     veterin
    1.60
    </i>
    1.59
    ୃ
    1.58
     OGSÅ
    1.55
    jaqueta
    1.52
    螄
    1.52
     preju
    1.51
    鹮
    1.50
     fashioned
    1.49
    Activations Density 0.003%

    No Known Activations