© 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. 14846
    Prev
    Next
    INDEX
    Explanations

    splash shares medium

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

    and S or **S**

    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
    是什么
    0.37
    有着
    0.37
     মিনি
    0.36
    ){}
    0.36
     বহুম
    0.36
    程序员
    0.36
    ইউ
    0.35
     transforms
    0.34
     poles
    0.34
     struts
    0.34
    POSITIVE LOGITS
    exercice
    0.41
    ći
    0.39
     Sulfur
    0.39
     अकेला
    0.39
     Weed
    0.39
     BOP
    0.39
    碖
    0.38
     Exercises
    0.38
    oliko
    0.38
     suppuration
    0.38
    Activations Density 0.000%

    No Known Activations