© 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. 101983
    Prev
    Next
    INDEX
    Explanations

    "Rap" followed by specific terms

    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
    诹
    -2.97
    閙
    -2.83
    ですが
    -2.73
     ushered
    -2.72
     {
    -2.69
     —
    -2.61
     velho
    -2.58
     compelled
    -2.55
    ± 
    -2.53
     และ
    -2.50
    POSITIVE LOGITS
    a
    3.73
    e
    2.91
     帅气
    2.58
    D
    2.47
    Ꮏ
    2.45
     комнате
    2.44
     pidiendo
    2.39
     realizando
    2.34
    the
    2.33
    鬈
    2.33
    Activations Density 0.009%

    No Known Activations