© 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. 228854
    Prev
    Next
    INDEX
    Explanations

    causing XP

    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
    ᱷ
    0.49
    ତ୍
    0.46
     ござい
    0.46
    ্ম্ম
    0.46
    дку
    0.46
     ಮತ್ತ
    0.46
     ক্রিকেটার
    0.45
    琺
    0.45
    ԁ
    0.45
    নীতির
    0.45
    POSITIVE LOGITS
     veröffentlicht
    0.48
     zehn
    0.47
    发表
    0.46
     발표
    0.46
     Alberta
    0.46
     Coyote
    0.45
     kamera
    0.44
     “
    0.44
     Hewlett
    0.44
     punkt
    0.42
    Activations Density 0.001%

    No Known Activations