© 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. 17942
    Prev
    Next
    INDEX
    Explanations

    systems and domains

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

    informally, calcium, satirical, farming

    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
     coarser
    0.46
     moveTo
    0.46
    workspaceFolder
    0.46
     invoke
    0.45
    v
    0.45
     exiting
    0.45
    tir
    0.45
    sı
    0.45
     doings
    0.44
     odv
    0.44
    POSITIVE LOGITS
    Params
    0.48
     نظام
    0.46
     سسٹم
    0.45
    Domain
    0.45
    Omega
    0.45
    搂
    0.43
    プラ
    0.43
     系统
    0.42
    <unused1038>
    0.42
    Domains
    0.41
    Activations Density 0.000%

    No Known Activations