© 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. 68609
    Prev
    Next
    INDEX
    Explanations

    percentage and foreign cities

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

    legal or professional roles

    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
    羋
    0.50
     Fundraising
    0.48
     PPAR
    0.47
    जरीवाल
    0.44
    𝐟
    0.43
     Áng
    0.42
     období
    0.41
     Diplomacy
    0.41
     folyam
    0.41
     সমর
    0.41
    POSITIVE LOGITS
    问
    0.50
    不知道
    0.49
     প্রশ্ন
    0.46
    ennie
    0.44
    ク
    0.44
    オーク
    0.44
    Ville
    0.43
    城市的
    0.43
    Percent
    0.42
    ม
    0.42
    Activations Density 0.000%

    No Known Activations