© 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. 636
    Prev
    Next
    INDEX
    Explanations

    contractual terms and agreements

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

    payment terms and agreement clauses

    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
     Sereth
    0.70
    皞
    0.69
    恐惧
    0.66
    攻击
    0.65
    图形
    0.64
    爱好者
    0.63
    鸴
    0.62
    边缘
    0.62
     Größe
    0.62
    痉
    0.61
    POSITIVE LOGITS
     contractual
    1.13
     payments
    1.05
    payments
    0.98
     agreed
    0.96
    contract
    0.92
    payment
    0.92
     contract
    0.91
     covenants
    0.85
     payment
    0.84
    契約
    0.80
    Activations Density 0.298%

    No Known Activations