© 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. 156334
    Prev
    Next
    INDEX
    Explanations

    powered by data

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

    AI Assistant, technical terms

    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
     развития
    0.49
    規劃
    0.48
     그래프
    0.47
    セール
    0.47
     разработки
    0.46
     ਵਿੱਚ
    0.46
     डाव
    0.46
    沘
    0.46
    Ⲛ
    0.45
    Khud
    0.45
    POSITIVE LOGITS
     Aqua
    0.46
     Shoes
    0.46
     ump
    0.44
     ideally
    0.43
    动脉
    0.42
     powered
    0.42
     Preferably
    0.42
     injector
    0.41
     ion
    0.41
     dioxide
    0.41
    Activations Density 0.001%

    No Known Activations