© 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. 240805
    Prev
    Next
    INDEX
    Explanations

    political or business entities

    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
    <0x80>
    0.48
     наших
    0.47
    0
    0.47
     ماضی
    0.46
    생활
    0.44
    ொ
    0.43
    什
    0.43
    店内
    0.42
    氈
    0.42
     تبدیلی
    0.42
    POSITIVE LOGITS
     betrachtet
    0.51
     bestimmt
    0.48
     solic
    0.48
     sucedió
    0.47
     Ahmad
    0.45
     accidentally
    0.45
     جس
    0.45
     helplessly
    0.44
     mantra
    0.44
     schreibt
    0.43
    Activations Density 0.001%

    No Known Activations