© 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. 84933
    Prev
    Next
    INDEX
    Explanations

    pseudocode examples

    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
    THISDAY
    -0.90
     haji
    -0.85
     SENIOR
    -0.81
    ୍
    -0.80
    zondere
    -0.79
     GREEK
    -0.78
     vidi
    -0.78
     satria
    -0.76
     uchiha
    -0.75
    ysql
    -0.74
    POSITIVE LOGITS
     pseudo
    4.44
    pseudo
    3.95
    Pseudo
    3.78
     Pseudo
    3.72
    伪
    3.03
     psu
    2.56
     pseud
    2.38
    PSE
    2.09
    pseud
    2.02
     Algorithm
    1.95
    Activations Density 0.166%

    No Known Activations