© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42804
    Prev
    Next
    INDEX
    Explanations

    Russia in geopolitical contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -2.42
    on
    -2.41
    ндарт
    -2.34
     or
    -2.28
    饪
    -2.22
     позволяет
    -2.19
    x
    -2.19
    地に
    -2.16
    旅程
    -2.13
    比如说
    -2.13
    POSITIVE LOGITS
    </b>
    2.50
     Después
    2.44
    遢
    2.36
    鲠
    2.34
    та
    2.31
     doença
    2.27
     größ
    2.22
    actéristi
    2.14
     Après
    2.14
     slaps
    2.09
    Activations Density 0.007%

    No Known Activations