© 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. 198410
    Prev
    Next
    INDEX
    Explanations

    Samaritan

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

    marginalized jewish society

    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
     वोट
    0.48
     крас
    0.42
    игры
    0.42
     людей
    0.42
     хочу
    0.41
     кино
    0.41
    🟢
    0.41
    ры
    0.40
     Initiatives
    0.39
     рост
    0.39
    POSITIVE LOGITS
     STRICT
    0.49
     garantie
    0.47
     physiologique
    0.46
    遗传
    0.45
    TU
    0.42
     rę
    0.42
     physiologically
    0.41
     sév
    0.41
     spécialement
    0.41
     apparently
    0.41
    Activations Density 0.004%

    No Known Activations