© 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-16K
    7. 12740
    Prev
    Next
    INDEX
    Explanations

    legal and contractual terms

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

    contract law and agreements

    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_16k_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
     அறிகுற
    0.47
    骧
    0.46
     कंड
    0.44
     voters
    0.44
    erving
    0.44
     Investigator
    0.44
     investigator
    0.43
    淥
    0.43
    ั่วโมง
    0.42
    risome
    0.42
    POSITIVE LOGITS
    法律
    0.61
     القانون
    0.57
     Contracts
    0.55
     Bentham
    0.55
    法的
    0.55
     contractile
    0.55
    契約
    0.54
     giurid
    0.54
     Vertrags
    0.53
     jurisprudence
    0.52
    Activations Density 0.169%

    No Known Activations