© 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. 65716
    Prev
    Next
    INDEX
    Explanations

    political followed by a concept

    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
     conoz
    -0.88
    到的
    -0.84
    ír
    -0.82
    ’
    -0.82
     terrifying
    -0.80
    政府
    -0.80
    érieurs
    -0.77
    DoubleQuotes
    -0.77
     now
    -0.76
     medicina
    -0.76
    POSITIVE LOGITS
     correctness
    1.30
     Correct
    1.27
    Brighton
    1.24
     scientist
    1.19
    political
    1.11
     subdivisions
    1.09
    correct
    1.01
     attiva
    0.99
     partij
    0.99
     scientists
    0.99
    Activations Density 0.019%

    No Known Activations