© 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. 4262
    Prev
    Next
    INDEX
    Explanations

    governmental and planning districts

    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
     HOS
    -0.83
    キャベツ
    -0.83
     دارید
    -0.80
    neigh
    -0.79
     CLP
    -0.79
    going
    -0.77
    deauna
    -0.71
     CPF
    -0.71
     радость
    -0.71
    tific
    -0.70
    POSITIVE LOGITS
     region
    1.59
     Region
    1.42
     regional
    1.37
     Regional
    1.29
     consortium
    1.12
     región
    1.11
     basin
    1.10
    region
    1.09
    Region
    1.09
     councils
    1.09
    Activations Density 0.033%

    No Known Activations