© 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. 188204
    Prev
    Next
    INDEX
    Explanations

    taught how, weeded out, continued work

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

    launch/start/initiate

    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
    RUP
    0.50
    REA
    0.48
    URI
    0.47
    SEP
    0.47
    IRI
    0.47
    class
    0.46
    𝗕
    0.46
    URN
    0.46
    ofile
    0.46
    Painted
    0.46
    POSITIVE LOGITS
     obten
    0.51
    发起
    0.48
    火箭
    0.46
     родителей
    0.46
    发动
    0.45
     získ
    0.45
    잌
    0.45
     wọn
    0.44
     amassed
    0.44
    期望
    0.43
    Activations Density 0.001%

    No Known Activations