© 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. 37630
    Prev
    Next
    INDEX
    Explanations

    legal proceedings and filings

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

    legal and court proceedings

    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
     уголов
    0.69
     kriminal
    0.68
    刑
    0.63
    罪
    0.61
     convict
    0.60
    riminal
    0.60
    criminals
    0.59
    criminal
    0.58
    죄
    0.58
     преступ
    0.58
    POSITIVE LOGITS
     রিসার্চ
    0.48
     time
    0.45
     Oral
    0.43
     Noodles
    0.43
     O
    0.43
    的气
    0.43
     conference
    0.42
    的時間
    0.42
     Research
    0.42
     Lit
    0.42
    Activations Density 0.082%

    No Known Activations