© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 23610
    Prev
    Next
    INDEX
    Explanations

    HTML/CSS layout and style classes

    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
    えっ
    -1.77
    ごめん
    -1.61
    あぁ
    -1.52
    マジで
    -1.50
    久し
    -1.48
     voorwaarden
    -1.48
    すっ
    -1.47
    さぁ
    -1.40
    為に
    -1.40
    あー
    -1.37
    POSITIVE LOGITS
    などは
    1.32
    などが
    1.27
     добраться
    1.25
    問題は
    1.23
    Однако
    1.10
    といいます
    1.09
    かで
    1.08
    นม
    1.07
    m
    1.06
    そうですが
    1.05
    Activations Density 0.039%

    No Known Activations