© 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. 10-GEMMASCOPE-RES-131K
    7. 28983
    Prev
    Next
    INDEX
    Explanations

    political leader or official

    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_10/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
     from
    -1.78
     this
    -1.48
     in
    -1.41
     always
    -1.29
     romano
    -1.25
     determina
    -1.22
     censi
    -1.18
     it
    -1.16
     These
    -1.16
     continuo
    -1.10
    POSITIVE LOGITS
    even
    1.43
     Даже
    1.09
    nebo
    1.03
    給你
    1.02
     zumindest
    1.02
     другую
    1.01
    ℭ
    1.01
     tiveram
    1.00
     براي
    1.00
     Possibly
    1.00
    Activations Density 0.181%

    No Known Activations