© 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. 191402
    Prev
    Next
    INDEX
    Explanations

    powder guard, production line, market outlook

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

    profits, Engineer, didn't, forever, counts, especially, Prompt, question, account

    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
    驯
    0.47
    紋
    0.47
    诸多
    0.45
    诛
    0.44
    人们
    0.43
    地图
    0.43
    过的
    0.43
    城乡
    0.43
    纹
    0.43
    总结
    0.42
    POSITIVE LOGITS
     Zone
    0.59
     Type
    0.55
     commencing
    0.54
     machined
    0.54
     devem
    0.53
     elles
    0.53
     Supervisor
    0.53
     competente
    0.53
     O
    0.52
     doit
    0.52
    Activations Density 0.003%

    No Known Activations