© 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. 601
    Prev
    Next
    INDEX
    Explanations

    shell commands

    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
    央
    -0.72
    
    -0.71
    庫
    -0.68
    ribute
    -0.66
    arası
    -0.66
     Cite
    -0.65
     poulet
    -0.65
    емся
    -0.65
     plástica
    -0.65
     Loyalty
    -0.63
    POSITIVE LOGITS
     ls
    2.38
    ls
    2.25
     cd
    2.00
     LS
    2.00
    rm
    1.95
    cd
    1.92
     rm
    1.91
     cp
    1.91
    LS
    1.82
    cp
    1.80
    Activations Density 0.193%

    No Known Activations