© 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. 66799
    Prev
    Next
    INDEX
    Explanations

    qualities or states

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

    overcome repulsion

    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
    、
    0.55
    幼儿园
    0.49
    的
    0.46
     buss
    0.46
     subcontractors
    0.44
    简洁
    0.44
     subcontract
    0.44
    蹼
    0.43
    和服务
    0.43
     links
    0.43
    POSITIVE LOGITS
    due
    0.54
    when
    0.49
    characterized
    0.49
    reliant
    0.48
     může
    0.47
    lose
    0.47
     peculiarity
    0.47
     harina
    0.47
    bbene
    0.47
     vanwege
    0.47
    Activations Density 0.000%

    No Known Activations