© 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. 172361
    Prev
    Next
    INDEX
    Explanations

    will disclose

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

    geopolitical entities and their concerns

    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
     ভাগ্যবান
    0.46
     любить
    0.46
    ച്ചത്
    0.45
    ኚ
    0.44
    村民
    0.43
    如果是
    0.43
     빙
    0.43
    кування
    0.41
    支払い
    0.41
     மனைவி
    0.41
    POSITIVE LOGITS
     comes
    0.47
     invites
    0.44
     gets
    0.44
     explores
    0.41
     يُ
    0.41
     ‍
    0.39
     estão
    0.38
     começ
    0.38
    marketing
    0.38
     منهج
    0.38
    Activations Density 0.001%

    No Known Activations