© 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. 42844
    Prev
    Next
    INDEX
    Explanations

    change completed or ongoing

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

    is/are verbs followed by past participles

    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
     knew
    0.47
     jì
    0.44
    ∋
    0.42
     þei
    0.42
     নিজেও
    0.42
    ствием
    0.41
    เป็น
    0.41
    สนับสนุน
    0.40
    媤
    0.40
     явля
    0.40
    POSITIVE LOGITS
     reborn
    0.51
    blown
    0.48
     unrelenting
    0.47
     expelled
    0.45
     rediscovered
    0.45
    发现
    0.44
     Seen
    0.43
     resurrected
    0.43
     ईंधन
    0.41
     unleashed
    0.40
    Activations Density 0.108%

    No Known Activations