© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 127957
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and parties

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

    legal terms and parties

    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
     বদলে
    0.80
     สร้าง
    0.76
    สร้าง
    0.70
    Grazie
    0.66
    Những
    0.65
    逺
    0.64
    团队
    0.64
    网络
    0.63
    🦁
    0.63
     помогут
    0.62
    POSITIVE LOGITS
     pursuant
    0.98
     appellant
    0.96
     defendant
    0.90
     appellants
    0.89
     Appellant
    0.87
     codef
    0.87
     plaintiff
    0.86
     Plaintiff
    0.84
     appellees
    0.84
     Pursuant
    0.84
    Activations Density 0.058%

    No Known Activations