© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104904
    Prev
    Next
    INDEX
    Explanations

    actions following "to"

    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
     unquestionably
    -2.02
    她说
    -1.93
    普通的
    -1.91
     uiteindelijk
    -1.90
     some
    -1.88
     weirdly
    -1.83
     oftentimes
    -1.82
    主婦
    -1.82
    我们会
    -1.82
    先代
    -1.80
    POSITIVE LOGITS
    ↵↵
    1.88
    re
    1.87
     BadRequest
    1.73
    ﮨ
    1.69
     remboursement
    1.63
     maniere
    1.63
     pinggang
    1.63
    捶
    1.61
    how
    1.60
     durer
    1.59
    Activations Density 0.053%

    No Known Activations