© 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. 198131
    Prev
    Next
    INDEX
    Explanations

    time, money, planning, environment, technology

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

    list items or code blocks

    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
    Z
    0.47
     Z
    0.45
     sequester
    0.43
     commissioned
    0.42
     подо
    0.42
     redesigned
    0.42
    ﷼
    0.42
    つ
    0.41
     competent
    0.40
    ？？
    0.40
    POSITIVE LOGITS
    cephalus
    0.47
    VRDR
    0.47
     jati
    0.46
     وقت
    0.46
     پرورش
    0.45
    štění
    0.43
    ത്താ
    0.43
     reals
    0.43
     بات
    0.42
    merksamkeit
    0.42
    Activations Density 0.001%

    No Known Activations