© 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. 45606
    Prev
    Next
    INDEX
    Explanations

    real estate and specific entities

    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
     fitted
    -0.80
    gráficos
    -0.80
    стной
    -0.78
     เส
    -0.77
     неожидан
    -0.77
    lame
    -0.75
    כם
    -0.71
     Assist
    -0.71
     vede
    -0.70
    imperial
    -0.70
    POSITIVE LOGITS
    衛隊
    0.79
    rips
    0.78
     menikah
    0.77
     Documentary
    0.71
    Protest
    0.70
     étanche
    0.70
    omat
    0.69
     originaire
    0.69
     крестьян
    0.69
    nature
    0.69
    Activations Density 0.007%

    No Known Activations