© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210518
    Prev
    Next
    INDEX
    Explanations

    Russia Ukraine conflict accusations

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

    Ukrainian strikes and forces

    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
     ευρώ
    0.45
    議題
    0.45
     الفاظ
    0.43
    ਗ
    0.42
    currencies
    0.42
    ㄝ
    0.42
     روسی
    0.41
    かれている
    0.41
    торой
    0.40
    狼
    0.40
    POSITIVE LOGITS
     fly
    0.46
     Gulf
    0.44
     distanceFrom
    0.43
     damaging
    0.43
     IPT
    0.41
     damage
    0.41
     netting
    0.41
     zon
    0.41
     Eaton
    0.41
     Air
    0.40
    Activations Density 0.002%

    No Known Activations