© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7677
    Prev
    Next
    INDEX
    Explanations

    assign a

    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
    ๑
    0.65
     י
    0.64
     または
    0.63
     Atau
    0.61
     หรือ
    0.61
     ニ
    0.60
     Ма
    0.58
     /
    0.58
     מר
    0.58
     Э
    0.56
    POSITIVE LOGITS
    helloworld
    0.66
     якобы
    0.65
    甄
    0.63
    buttonclick
    0.62
     নাকি
    0.60
     SECUR
    0.57
    ご飯
    0.55
     ridicu
    0.55
     परहेज
    0.55
     nonfiction
    0.54
    Activations Density 0.333%

    No Known Activations