© 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. 237
    Prev
    Next
    INDEX
    Explanations

    common word pairings

    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
     великолеп
    -1.95
    😻
    -1.67
    💘
    -1.63
    ⽀
    -1.62
    🎊
    -1.59
    💓
    -1.53
    来讲
    -1.53
     iaitu
    -1.52
    Ꮠ
    -1.52
     triunfo
    -1.47
    POSITIVE LOGITS
     didn
    1.71
    </h2>
    1.66
     their
    1.62
     isn
    1.51
     already
    1.48
     это
    1.47
     they
    1.46
     дефек
    1.46
     that
    1.44
     tiene
    1.43
    Activations Density 0.083%

    No Known Activations