© 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. 83096
    Prev
    Next
    INDEX
    Explanations

    politicspartypoliticianspolitical

    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
    ությ
    -1.00
     Whilst
    -0.90
     (
    -0.88
     Danemark
    -0.84
    ,
    -0.82
     zawsze
    -0.80
     evtl
    -0.79
     Maybe
    -0.79
    sockfd
    -0.78
     Perhaps
    -0.78
    POSITIVE LOGITS
     [],
    1.04
     overarching
    1.02
     Tuesday
    1.02
    ゴリ
    0.98
    τως
    0.97
     cloths
    0.97
     Thursday
    0.96
    Procedimento
    0.95
     Investment
    0.92
     coron
    0.92
    Activations Density 0.018%

    No Known Activations