© 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. 47741
    Prev
    Next
    INDEX
    Explanations

    first word of a new phrase

    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
     allerlei
    -1.70
    žas
    -1.66
    ').
    -1.66
     zowel
    -1.63
     echte
    -1.53
    〖
    -1.52
    cée
    -1.50
     coke
    -1.49
    </b>
    -1.48
     ihtiyac
    -1.45
    POSITIVE LOGITS
    而非
    1.77
    というわけで
    1.66
    breviations
    1.65
     inserted
    1.61
     they
    1.58
     parco
    1.58
     singolo
    1.53
    ズニー
    1.53
    さてさて
    1.52
    樒
    1.51
    Activations Density 0.019%

    No Known Activations