© 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. 190585
    Prev
    Next
    INDEX
    Explanations

    transportation and service providers

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

    defend yourself

    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
    禳
    0.62
    反对
    0.56
    לית
    0.54
    在这个
    0.51
    出于
    0.50
    隗
    0.50
    לת
    0.49
    演唱
    0.49
    ונת
    0.47
    ی
    0.47
    POSITIVE LOGITS
     passengers
    0.54
     voyage
    0.48
    td
    0.48
     carpenters
    0.47
    tr
    0.46
     sailors
    0.46
     manufacturer
    0.46
     skates
    0.46
     voyageurs
    0.46
     masterpiece
    0.45
    Activations Density 0.000%

    No Known Activations