© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2773
    Prev
    Next
    INDEX
    Explanations

    developed by organization

    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_31_width_16k_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
    <unused100>
    0.56
    Przyp
    0.51
    IGNORE
    0.50
    Джо
    0.48
     nhớ
    0.48
    하세요
    0.47
    🤖
    0.47
    ')
    0.46
    Tienes
    0.46
    См
    0.46
    POSITIVE LOGITS
     orthodont
    0.56
     inten
    0.54
     four
    0.54
     oleh
    0.53
     high
    0.53
     eine
    0.52
     Microsoft
    0.52
     UNDP
    0.52
     three
    0.52
     limbo
    0.52
    Activations Density 0.163%

    No Known Activations