© 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. 210003
    Prev
    Next
    INDEX
    Explanations

    links to websites or information

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

    putting, while, destination, remember, skepticism, gallery, Custodian

    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
     Snapchat
    0.50
     LI
    0.49
    氀
    0.49
    子
    0.48
    Item
    0.48
    Util
    0.48
    ли
    0.47
     RAD
    0.47
     Cisco
    0.47
    不同
    0.47
    POSITIVE LOGITS
     seniority
    0.49
    ຝ
    0.46
     ຈ
    0.45
     exquisitely
    0.44
     회사
    0.44
     நன்மை
    0.44
     pubescence
    0.43
    də
    0.43
     eğer
    0.43
     प्लॉट
    0.43
    Activations Density 0.001%

    No Known Activations