© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 2409
    Prev
    Next
    INDEX
    Explanations

    purpose driven

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    我
    2.22
    ви
    1.99
    เรา
    1.87
    ü
    1.75
    rā
    1.71
    不錯
    1.65
     แ
    1.62
    ag
    1.61
    দৌ
    1.60
    ول
    1.59
    POSITIVE LOGITS
     havoc
    1.89
     खासा
    1.89
     acclaim
    1.88
     turístico
    1.85
     interchangeable
    1.84
     cornerstone
    1.82
    প্রণ
    1.82
     acreditar
    1.81
     свидетель
    1.78
     disgraced
    1.78
    Activations Density 0.035%

    No Known Activations