© 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. 90219
    Prev
    Next
    INDEX
    Explanations

    Russian history and geography

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

    Russian literature and history

    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
     ব্রিট
    0.51
    新加坡
    0.50
    lblCredits
    0.49
    लेरिया
    0.48
    তনাম
    0.47
    INUS
    0.46
    犾
    0.46
    会计
    0.46
     വൈറ
    0.45
    कारात्मक
    0.45
    POSITIVE LOGITS
     Russian
    0.81
    Russian
    0.73
     russian
    0.71
     러시아
    0.67
     Russia
    0.66
     Russians
    0.63
     Petersburg
    0.61
    russian
    0.61
     Rusia
    0.58
    ロシア
    0.58
    Activations Density 0.025%

    No Known Activations