© 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. 92510
    Prev
    Next
    INDEX
    Explanations

    mnemonic passphrase or word lists

    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
    aung
    -0.70
    ि
    -0.69
    itung
    -0.69
    実
    -0.67
    стройства
    -0.66
    íu
    -0.66
     menekan
    -0.66
    閏
    -0.65
     その
    -0.65
     votar
    -0.65
    POSITIVE LOGITS
     words
    1.60
     word
    1.52
    words
    1.30
     lists
    1.30
     list
    1.28
    lists
    1.20
    word
    1.14
    WORDS
    1.10
    Words
    1.09
     palabras
    1.06
    Activations Density 0.038%

    No Known Activations