© 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. 34-GEMMASCOPE-RES-131K
    7. 102538
    Prev
    Next
    INDEX
    Explanations

    dictionary keys and values

    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_34/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
     though
    -0.83
    ///**
    -0.77
     conférence
    -0.75
    嵯
    -0.75
    ﻭ
    -0.72
     бле
    -0.72
     मो
    -0.72
     rég
    -0.71
    medal
    -0.70
    駒
    -0.70
    POSITIVE LOGITS
    ζει
    0.89
     capelli
    0.80
    应该是
    0.77
    wego
    0.76
     Поэтому
    0.75
    össä
    0.75
    boden
    0.74
     Asien
    0.73
     adulter
    0.73
     fura
    0.73
    Activations Density 0.014%

    No Known Activations