© 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. 148040
    Prev
    Next
    INDEX
    Explanations

    wedding celebration

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

    if someone or assuming basic

    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
    ul
    0.56
    UN
    0.55
    ust
    0.52
    uck
    0.50
    …
    0.49
    um
    0.47
     bang
    0.47
    av
    0.47
    …).
    0.47
    ar
    0.47
    POSITIVE LOGITS
     irradi
    0.50
     يوليو
    0.49
    了一個
    0.47
     Tarifleri
    0.47
     itemscope
    0.46
     العمود
    0.46
     يونيو
    0.46
     ஆண்டில்
    0.45
     忄
    0.45
     பற்றிய
    0.45
    Activations Density 0.001%

    No Known Activations