© 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. 67090
    Prev
    Next
    INDEX
    Explanations

    economic and social systems

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

    arguments, client, unmatched, supports

    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
     Scoop
    0.44
     ಮು
    0.43
     Eiffel
    0.42
    σκο
    0.41
    鱷
    0.41
     Hop
    0.41
     battered
    0.41
     सपनों
    0.41
     ທ
    0.40
     带
    0.40
    POSITIVE LOGITS
     occupant
    0.49
     capitalism
    0.43
     occupants
    0.43
     aligns
    0.42
    associations
    0.42
     magist
    0.41
    economics
    0.41
    asis
    0.41
    jski
    0.40
     bourgeoisie
    0.40
    Activations Density 0.000%

    No Known Activations