© 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. 42962
    Prev
    Next
    INDEX
    Explanations

    put America first, hair removal

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

    capybara or alpaca pronunciation

    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
    edge
    0.46
    Edge
    0.46
     e
    0.45
     Edge
    0.45
     Euro
    0.41
     indemnity
    0.40
    地位
    0.39
     came
    0.39
     rangers
    0.38
     plan
    0.38
    POSITIVE LOGITS
     ASSEM
    0.64
    𝚇
    0.60
     ежедневно
    0.58
     прогнозы
    0.53
    ব্ল
    0.52
     чор
    0.52
     อ่าน
    0.51
     улучшения
    0.51
     આજ
    0.50
     թվ
    0.49
    Activations Density 0.000%

    No Known Activations