© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9607
    Prev
    Next
    INDEX
    Explanations

    law, politics, and society

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

    why and how

    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_40_width_16k_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
    less
    0.39
    ý
    0.39
    ńskim
    0.38
     -
    0.38
    si
    0.38
    ุก
    0.37
    í
    0.37
    σό
    0.36
    阪
    0.36
    alp
    0.36
    POSITIVE LOGITS
     Its
    0.65
     its
    0.62
     colonialism
    0.57
     SOCIETY
    0.56
     Politics
    0.55
    Its
    0.53
     Judaism
    0.53
    Politics
    0.52
     criminality
    0.51
     বাস্তবতা
    0.50
    Activations Density 0.088%

    No Known Activations