© 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. 86696
    Prev
    Next
    INDEX
    Explanations

    a [adjective or noun]

    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
     nè
    -1.77
    usually
    -1.73
    primarily
    -1.64
    generally
    -1.63
     mè
    -1.61
    鸸
    -1.59
    almost
    -1.55
    possibly
    -1.55
    basically
    -1.55
    obviously
    -1.54
    POSITIVE LOGITS
     through
    1.96
     as
    1.84
     perplexing
    1.80
     at
    1.66
     In
    1.66
     excessive
    1.60
     troubling
    1.59
     came
    1.55
     supremely
    1.55
     continual
    1.52
    Activations Density 0.025%

    No Known Activations