© 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. 213070
    Prev
    Next
    INDEX
    Explanations

    loans online, man who, teach them

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

    arrangement and flexibility

    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
     fête
    0.48
     rampage
    0.48
    ᵗ
    0.48
     x
    0.47
     están
    0.47
     narciss
    0.47
     forn
    0.46
     dív
    0.46
     paradise
    0.44
     युक्त
    0.44
    POSITIVE LOGITS
    সরকারী
    0.48
    इस
    0.47
    чого
    0.47
    ссив
    0.47
    啮
    0.45
    그
    0.45
    俥
    0.45
    इसके
    0.44
    مه
    0.43
     այդ
    0.43
    Activations Density 0.002%

    No Known Activations