© 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. 22305
    Prev
    Next
    INDEX
    Explanations

    legal rights and obligations

    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
    纽约
    0.64
    美国
    0.63
     নিউইয়
    0.62
    纬
    0.61
     драй
    0.60
     ameryka
    0.58
     amerik
    0.58
    स्टम
    0.57
    组件
    0.56
     Джей
    0.56
    POSITIVE LOGITS
     Decreto
    0.69
     touristic
    0.64
     jurid
    0.62
     القانون
    0.60
     prestations
    0.60
     €
    0.58
     Ministerio
    0.57
     decreto
    0.57
     Schengen
    0.56
     remuneration
    0.54
    Activations Density 0.066%

    No Known Activations