© 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. 2213
    Prev
    Next
    INDEX
    Explanations

    Digital followed by specific nouns

    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
     mangled
    -0.91
     cheia
    -0.89
    venge
    -0.89
     Groen
    -0.88
     balk
    -0.87
     intrepid
    -0.87
    éroport
    -0.86
    áním
    -0.85
     hapless
    -0.85
     folha
    -0.84
    POSITIVE LOGITS
    isation
    1.33
    ization
    1.26
    ized
    1.12
    ize
    1.07
     Deepak
    1.00
     デジタル
    0.97
    $
    0.96
     detox
    0.95
     Digital
    0.94
     Detox
    0.94
    Activations Density 0.019%

    No Known Activations