© 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. 2781
    Prev
    Next
    INDEX
    Explanations

    batch script

    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
    션
    0.67
    十分
    0.66
    的同时
    0.64
    nostic
    0.63
    ellis
    0.63
     substantiate
    0.63
     হুমায়
    0.63
    赊
    0.62
    ">,</
    0.61
    efully
    0.61
    POSITIVE LOGITS
    ులు
    0.79
    itecture
    0.77
    hhhh
    0.77
    ievement
    0.76
    ievements
    0.74
    ング
    0.71
    ádz
    0.71
    ఛ
    0.70
    hhh
    0.70
    ITECT
    0.68
    Activations Density 0.254%

    No Known Activations