© 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. 41-GEMMASCOPE-2-RES-65K
    7. 1618
    Prev
    Next
    INDEX
    Explanations

    to a large degree

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    uary
    0.49
    小さい
    0.48
    次に
    0.47
    完整的
    0.47
     Larger
    0.47
    uarine
    0.46
    谧
    0.46
     कह
    0.46
    ftan
    0.46
     Determined
    0.46
    POSITIVE LOGITS
     considerably
    2.73
     significantly
    2.72
     dramatically
    2.58
     drastically
    2.56
     greatly
    2.47
     substantially
    2.44
     markedly
    2.33
     значительно
    2.28
     tremendously
    2.22
     enormously
    2.17
    Activations Density 0.567%

    No Known Activations