© 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. 29303
    Prev
    Next
    INDEX
    Explanations

    moderate GOP politicians

    np_acts-logits-general · gemini-2.5-flash-lite

    moderate political discourse

    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
     Koll
    0.46
     marx
    0.43
     viscose
    0.42
     jakarta
    0.41
     Peoples
    0.40
    ریٹر
    0.40
     kapas
    0.39
     ¹
    0.39
     earthenware
    0.39
    ٗ
    0.39
    POSITIVE LOGITS
    moderate
    0.56
     moderate
    0.53
     moder
    0.48
    Moderate
    0.47
     Moderate
    0.46
    ън
    0.46
     moderator
    0.43
     GOP
    0.43
     abandon
    0.43
     PAST
    0.43
    Activations Density 0.084%

    No Known Activations