© 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. 168761
    Prev
    Next
    INDEX
    Explanations

    safety and control imperatives

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

    engagement engagement

    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
    \<^
    0.58
    MenuItems
    0.57
    Subsec
    0.55
     カ
    0.54
    MenuList
    0.54
     لی
    0.52
     ಹ
    0.51
    Menus
    0.50
    platten
    0.50
     کا
    0.50
    POSITIVE LOGITS
     architects
    0.49
     continents
    0.49
     turpis
    0.47
    誼
    0.47
     theologians
    0.45
    卷
    0.43
     creepy
    0.43
     politics
    0.42
     pioneering
    0.42
     twins
    0.42
    Activations Density 0.000%

    No Known Activations