© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 33346
    Prev
    Next
    INDEX
    Explanations

    geopolitical shifts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    粛
    0.46
     Bernardino
    0.44
    阌
    0.44
     Gandhiji
    0.41
     Accepts
    0.40
    と思って
    0.40
    reservoir
    0.40
     গান্ধ
    0.40
    SLE
    0.40
     Supervisors
    0.39
    POSITIVE LOGITS
     ع
    0.48
    s
    0.48
     مك
    0.46
    ك
    0.44
     уд
    0.44
     مركز
    0.43
     з
    0.43
    ра
    0.42
     кор
    0.42
     haka
    0.42
    Activations Density 0.001%

    No Known Activations