© 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. 131041
    Prev
    Next
    INDEX
    Explanations

    indulgent words and 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
    '
    -2.86
     medarbe
    -1.87
    睒
    -1.80
    '...
    -1.77
     begle
    -1.77
     So
    -1.70
    ceram
    -1.69
    ку
    -1.68
    ';
    -1.68
    ༐
    -1.66
    POSITIVE LOGITS
    Kondisi
    2.20
    Seperti
    2.16
    O
    2.13
    Dengan
    2.08
    Sekarang
    2.08
    Semua
    2.06
    Sebagai
    2.00
    Sudah
    1.97
    Meskipun
    1.95
    Sebelum
    1.94
    Activations Density 0.005%

    No Known Activations