© 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. 4356
    Prev
    Next
    INDEX
    Explanations

    verb followed by a or an

    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
     одного
    -0.94
     なく
    -0.94
     aplicada
    -0.93
     Gnaden
    -0.89
     limitada
    -0.88
     fortemente
    -0.86
     genética
    -0.85
     aplicado
    -0.85
     relacionada
    -0.85
     jemand
    -0.84
    POSITIVE LOGITS
     a
    2.84
     an
    1.43
     quite
    1.11
     Quite
    0.97
     SUCH
    0.96
     hilft
    0.94
    了些
    0.93
     such
    0.91
    stva
    0.91
    Quite
    0.91
    Activations Density 0.091%

    No Known Activations