© 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. 197330
    Prev
    Next
    INDEX
    Explanations

    by his grace

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

    likelihood of outcomes

    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
     t
    0.52
     dyd
    0.51
     Late
    0.50
    late
    0.49
     fato
    0.49
    owe
    0.48
    owego
    0.47
     da
    0.47
     owe
    0.46
     n
    0.46
    POSITIVE LOGITS
    쾅
    0.50
    곳
    0.50
    단체
    0.49
    긱
    0.49
    훼
    0.49
    竣
    0.48
    놓
    0.46
    宿舍
    0.46
    전거
    0.46
    원이
    0.46
    Activations Density 0.001%

    No Known Activations