© 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. 62171
    Prev
    Next
    INDEX
    Explanations

    religion, secularism, government

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

    secular religion or browser extensions

    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
     вещества
    0.41
    ⤥
    0.40
    涯
    0.39
     Riet
    0.38
     پە
    0.38
    Podcast
    0.38
    Summit
    0.38
    糬
    0.37
    Deaths
    0.37
    iques
    0.37
    POSITIVE LOGITS
     secular
    0.64
     Secular
    0.59
     religion
    0.44
     Religion
    0.43
     firefox
    0.42
    Religion
    0.42
    religion
    0.40
     choirs
    0.40
     liturg
    0.39
     balanced
    0.38
    Activations Density 0.034%

    No Known Activations