© 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. 149199
    Prev
    Next
    INDEX
    Explanations

    Russia and Ukraine relations

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

    shared historical origins and cultural kinship

    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
    ovíd
    0.52
    कोष्ठ
    0.48
     இழு
    0.47
    무리
    0.47
    Kund
    0.45
    șt
    0.45
    踌
    0.45
    Commander
    0.45
    Ꭽ
    0.44
    žil
    0.43
    POSITIVE LOGITS
     similarities
    0.52
     sovereignty
    0.50
     communism
    0.49
     kinship
    0.49
     syllables
    0.48
     nationalists
    0.48
     friendship
    0.47
     consequences
    0.46
     interdependence
    0.46
     cultural
    0.46
    Activations Density 0.001%

    No Known Activations