© 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. 104091
    Prev
    Next
    INDEX
    Explanations

    slovakia and slovak

    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
    OUTUBE
    -2.72
    亖
    -2.63
    鈈
    -2.44
    我一直
    -2.39
    瞜
    -2.31
    Ꮉ
    -2.28
    屨
    -2.23
    ௅
    -2.22
    鹛
    -2.20
    嫑
    -2.20
    POSITIVE LOGITS
    “
    2.80
    as
    2.64
     और
    2.48
    </h5>
    2.41
    」
    2.38
     \"
    2.36
     \&
    2.30
    '>
    2.30
     '
    2.19
    .“
    2.19
    Activations Density 0.005%

    No Known Activations