© 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. 86947
    Prev
    Next
    INDEX
    Explanations

    descriptive words or phrases

    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
    -2.02
     at
    -1.94
     may
    -1.67
     like
    -1.63
     a
    -1.61
    哟
    -1.61
     each
    -1.59
     the
    -1.55
     both
    -1.54
     good
    -1.52
    POSITIVE LOGITS
     ofte
    1.46
     WIL
    1.42
    teens
    1.40
    ⬈
    1.39
     dando
    1.38
    偶尔
    1.38
    <bos>
    1.37
     巾
    1.34
     NYU
    1.34
    рую
    1.34
    Activations Density 0.090%

    No Known Activations