© 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. 66279
    Prev
    Next
    INDEX
    Explanations

    law or contract

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

    disclosed excluded disallowed

    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
     гене
    0.51
     것을
    0.50
    uyente
    0.48
     महत्त्व
    0.47
     preguntas
    0.47
     инстру
    0.46
     ませ
    0.46
    ᠨ
    0.46
     국제
    0.46
     proteínas
    0.46
    POSITIVE LOGITS
          
    0.43
     disclosed
    0.42
     had
    0.42
    控
    0.42
    ဆို
    0.42
     ![
    0.41
     forg
    0.41
     normalised
    0.41
     mirrored
    0.40
     severed
    0.40
    Activations Density 0.001%

    No Known Activations