© 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. 15350
    Prev
    Next
    INDEX
    Explanations

    care of sick

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

    historical events and critical descriptions

    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
     պատ
    0.51
     তর
    0.51
     ವಿಶ
    0.47
     ”
    0.46
     appreciates
    0.46
     bill
    0.45
     نوشته
    0.45
     encapsulates
    0.45
     say
    0.45
     WASHINGTON
    0.44
    POSITIVE LOGITS
    辍
    0.50
    疟
    0.48
    嚶
    0.47
    鬯
    0.46
     Dutt
    0.45
    gouv
    0.44
    Giving
    0.44
    รุ่น
    0.43
    趨
    0.42
    𖥔
    0.42
    Activations Density 0.000%

    No Known Activations