© 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. 21861
    Prev
    Next
    INDEX
    Explanations

    invention, integrated system

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

    method for 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
    blos
    0.44
    犠
    0.41
     constituent
    0.40
    Source
    0.40
    Due
    0.40
    Mah
    0.40
    ties
    0.39
     Systeme
    0.38
    Potential
    0.38
    瑣
    0.38
    POSITIVE LOGITS
    破解
    0.48
     बिजली
    0.48
     электро
    0.47
    安卓
    0.45
    авто
    0.45
    加密
    0.44
     điện
    0.43
    路由
    0.43
    اور
    0.43
     电
    0.43
    Activations Density 0.001%

    No Known Activations