© 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. 115439
    Prev
    Next
    INDEX
    Explanations

    CJ followed by names

    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
    篷
    -0.79
     zwischen
    -0.77
     kuma
    -0.77
     BSP
    -0.77
     эпо
    -0.76
     washers
    -0.76
    Sle
    -0.75
    onge
    -0.74
     parmi
    -0.73
    vase
    -0.73
    POSITIVE LOGITS
     CJ
    1.08
    CJ
    0.84
     Infectious
    0.73
    cj
    0.71
     ještě
    0.71
     demonstrate
    0.70
     перспекти
    0.69
     demonstrates
    0.69
    認識
    0.69
    世話
    0.68
    Activations Density 0.013%

    No Known Activations