© 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. 580
    Prev
    Next
    INDEX
    Explanations

    hit shallow rocks

    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
    faker
    -0.79
    MMMM
    -0.79
    totalPage
    -0.76
     منظ
    -0.76
     gazelle
    -0.75
     panas
    -0.74
     fusca
    -0.74
     acetic
    -0.73
     seawater
    -0.73
    Мор
    -0.73
    POSITIVE LOGITS
     shallow
    2.45
     rocks
    2.25
     reef
    1.98
     reefs
    1.84
    浅
    1.77
     sho
    1.74
    rocks
    1.73
    shallow
    1.68
     Rocks
    1.56
    淺
    1.56
    Activations Density 0.035%

    No Known Activations