© 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. 48262
    Prev
    Next
    INDEX
    Explanations

    Dragon Ball and One Piece titles

    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
    Karakteristik
    -1.86
    Kenapa
    -1.79
    Kelebihan
    -1.66
    Secara
    -1.63
    Hanya
    -1.61
    Bukan
    -1.57
    Meskipun
    -1.55
    Selanjutnya
    -1.54
    Kondisi
    -1.52
    Adapun
    -1.51
    POSITIVE LOGITS
     to
    1.76
     næste
    1.55
    jacke
    1.52
     klokken
    1.45
    EROS
    1.44
    ͍
    1.43
    tě
    1.41
    ONES
    1.35
     thanks
    1.35
     hvilket
    1.34
    Activations Density 0.016%

    No Known Activations