© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 2523
    Prev
    Next
    INDEX
    Explanations

    geopolitical interventions and sanctions

    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_40_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
     physiologique
    0.58
    删
    0.57
     ریاضی
    0.53
    Trimethyl
    0.53
    纹
    0.52
     Statistic
    0.51
    霭
    0.49
    晕
    0.48
     czynności
    0.48
    图形
    0.47
    POSITIVE LOGITS
     NATO
    1.29
     sanctions
    1.27
    NATO
    1.16
     geopolitical
    1.11
     diplomatic
    1.10
     diplomacy
    1.09
     humanitarian
    1.06
     Putin
    1.05
     geopol
    1.04
     санк
    1.02
    Activations Density 0.051%

    No Known Activations