© 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. 55740
    Prev
    Next
    INDEX
    Explanations

    code namespaces and types

    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
     so
    -1.57
    幸いです
    -1.07
    所以
    -1.02
     soit
    -1.00
     миллионов
    -0.99
     that
    -0.98
     not
    -0.97
     поэтому
    -0.96
     não
    -0.95
     nên
    -0.95
    POSITIVE LOGITS
     there
    1.18
     visu
    1.04
    见状
    1.03
    übt
    1.02
    âce
    1.00
     vinto
    0.98
    ƭ
    0.97
    textStyle
    0.96
    ⁦
    0.96
     там
    0.94
    Activations Density 0.025%

    No Known Activations