© 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. 2229
    Prev
    Next
    INDEX
    Explanations

    address this issue or gap

    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
     the
    -1.96
     они
    -1.64
    Their
    -1.43
     их
    -1.40
    This
    -1.20
    this
    -1.18
    their
    -1.12
     все
    -1.09
     сами
    -1.08
    所
    -1.08
    POSITIVE LOGITS
    filas
    0.98
    哙
    0.98
    めました
    0.96
     четырех
    0.95
    ękuję
    0.93
    tubo
    0.92
     виправи
    0.89
    mejores
    0.89
     kekasih
    0.88
    alcool
    0.88
    Activations Density 0.124%

    No Known Activations