© 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. 57192
    Prev
    Next
    INDEX
    Explanations

    historical empires and figures

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

    Mongol conquests and raids

    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
    发展的
    0.48
    benzoic
    0.46
    Ế
    0.44
     hacía
    0.43
     мона
    0.42
    纷
    0.42
     holomorphic
    0.41
    廛
    0.41
    ГА
    0.41
    ianic
    0.40
    POSITIVE LOGITS
     devast
    0.55
     Banglades
    0.55
     CENT
    0.50
     Mongolia
    0.49
     devastated
    0.47
     Islamabad
    0.46
     grasslands
    0.46
     incendi
    0.46
     grassland
    0.46
     pakistan
    0.45
    Activations Density 0.015%

    No Known Activations