© 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. 98592
    Prev
    Next
    INDEX
    Explanations

    doi, copyright, license

    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
    gridx
    -0.81
     briefed
    -0.78
     coffe
    -0.77
    odetic
    -0.75
     Fase
    -0.74
    zman
    -0.73
    loth
    -0.72
     Desc
    -0.71
    po
    -0.71
     ал
    -0.71
    POSITIVE LOGITS
     zru
    0.91
     могат
    0.85
     Menon
    0.81
    ):(
    0.79
    Senator
    0.78
    اله
    0.78
     tör
    0.75
     LeBlanc
    0.75
     egenskaper
    0.75
    Reasons
    0.74
    Activations Density 0.011%

    No Known Activations