© 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. 8848
    Prev
    Next
    INDEX
    Explanations

    transformation and awareness

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

    future capabilities and awareness

    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
     excellent
    0.52
     commer
    0.48
     +
    0.48
     所以
    0.47
     &
    0.46
    ющи
    0.46
     good
    0.45
     좋은
    0.45
     lemonade
    0.44
    ですので
    0.44
    POSITIVE LOGITS
     осозна
    0.61
    意识到
    0.59
    顫
    0.58
     rethink
    0.57
     인식
    0.57
    evolving
    0.55
     উপলব্ধি
    0.55
     понима
    0.53
     aware
    0.52
    瞠
    0.52
    Activations Density 0.013%

    No Known Activations