© 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. 1354
    Prev
    Next
    INDEX
    Explanations

    legal and historical contexts

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

    facts about entities

    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
    我们的
    0.55
     nostre
    0.52
    我们需要
    0.51
     нашем
    0.50
    我們的
    0.50
    女
    0.50
     naszym
    0.47
    cę
    0.47
     trzeba
    0.47
    正确的
    0.47
    POSITIVE LOGITS
     /ˈ
    0.57
    ,[
    0.50
     Encyclopædia
    0.49
     colloqu
    0.49
     mostly
    0.47
     publicized
    0.47
     Wikipedia
    0.47
     شده‌است
    0.46
     செயற்ப
    0.45
     controvers
    0.45
    Activations Density 0.254%

    No Known Activations