© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129390
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    
    -1.88
     you
    -1.85
    赜
    -1.84
     նաև
    -1.83
     atrav
    -1.69
    ANCIAL
    -1.68
     recém
    -1.65
     áng
    -1.64
    の新
    -1.63
     woda
    -1.62
    POSITIVE LOGITS
     than
    1.58
    （※
    1.48
     ONLY
    1.48
    ｢
    1.45
     "
    1.45
     an
    1.43
    <bos>
    1.42
    ！！！！
    1.41
     be
    1.37
     can
    1.34
    Activations Density 0.558%

    No Known Activations