© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 19201
    Prev
    Next
    INDEX
    Explanations

    political or moral concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    0
    0.42
    *
    0.41
    3
    0.39
    2
    0.38
    è
    0.38
     I
    0.38
     时
    0.37
    а
    0.36
     one
    0.36
     a
    0.35
    POSITIVE LOGITS
     politiques
    0.46
     politici
    0.46
     políticos
    0.46
     politič
    0.45
     politik
    0.44
     രാഷ്ട്രീയ
    0.44
     arrogant
    0.44
     wrongdoing
    0.44
     politische
    0.44
     políticas
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.