© 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. 163802
    Prev
    Next
    INDEX
    Explanations

    y or Y at start of words/phrases

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

    equations of y

    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
     Promote
    0.45
    สำคัญ
    0.44
    ämp
    0.43
    凿
    0.43
     penting
    0.42
    opyran
    0.42
     Important
    0.41
    াশ
    0.41
     ราศี
    0.41
     membuka
    0.41
    POSITIVE LOGITS
    Regression
    0.44
    Matching
    0.43
     y
    0.42
    Vertical
    0.42
     advisors
    0.40
    يلات
    0.40
    Goal
    0.40
    ಾಗಿ
    0.39
    𝑦
    0.39
     তত্ত্বাব
    0.38
    Activations Density 0.014%

    No Known Activations