© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81894
    Prev
    Next
    INDEX
    Explanations

    court appearances, regulations, Pt formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ostęp
    0.55
     Цена
    0.45
    对
    0.45
    下載
    0.45
    م
    0.44
    收购
    0.44
    灭
    0.44
    መ
    0.44
    铳
    0.44
    下载
    0.43
    POSITIVE LOGITS
     thư
    0.39
     ಭ
    0.38
     oub
    0.37
     Suf
    0.37
     coi
    0.36
    tif
    0.36
     doublet
    0.36
     appropriately
    0.35
     extrinsic
    0.35
     thi
    0.35
    Activations Density 0.001%

    No Known Activations