© 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. 52788
    Prev
    Next
    INDEX
    Explanations

    vpn, predictions, propecia, bandwidth, canada, casino

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

    from now on

    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
     повер
    0.44
    咾
    0.44
    乆
    0.42
     відпо
    0.41
    穌
    0.40
    蓑
    0.40
     давайте
    0.39
    教材
    0.39
    плення
    0.39
    蓍
    0.39
    POSITIVE LOGITS
    remove
    0.46
     largest
    0.46
    red
    0.45
    machine
    0.44
     machine
    0.42
    Largest
    0.42
    main
    0.41
    hat
    0.41
     hundred
    0.41
    include
    0.40
    Activations Density 0.028%

    No Known Activations