© 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. 60888
    Prev
    Next
    INDEX
    Explanations

    What's phrases

    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
    kval
    -0.80
    étique
    -0.78
    宏
    -0.78
    warted
    -0.77
    necess
    -0.76
     aikaa
    -0.75
    incen
    -0.75
     zbior
    -0.75
    jaros
    -0.75
    حاد
    -0.74
    POSITIVE LOGITS
    istas
    0.99
    vian
    0.94
     doin
    0.86
     encuentran
    0.84
    ッテ
    0.83
    lv
    0.82
     Relic
    0.82
    ww
    0.81
     doings
    0.80
     deixou
    0.79
    Activations Density 0.029%

    No Known Activations