© 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. 45571
    Prev
    Next
    INDEX
    Explanations

    winning numbers drawn

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

    winning lottery numbers

    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
    small
    0.41
     প্রদেশে
    0.41
     اخي
    0.41
     colds
    0.39
    繖
    0.39
    運輸
    0.39
    淥
    0.39
     PCs
    0.39
    knowing
    0.39
     pc
    0.38
    POSITIVE LOGITS
    きた
    0.46
    事实
    0.45
     vienen
    0.45
    ִ
    0.45
     vengono
    0.45
     recounted
    0.45
     unveiled
    0.44
    进行了
    0.43
     publiée
    0.43
     Gord
    0.43
    Activations Density 0.001%

    No Known Activations