© 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. 16379
    Prev
    Next
    INDEX
    Explanations

    aim to simplify

    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
    一个个
    0.62
     লইয়া
    0.59
     milhares
    0.58
    无数
    0.52
    න
    0.50
     thousands
    0.49
     Thousands
    0.48
    Thousands
    0.48
     decenas
    0.48
    廉
    0.48
    POSITIVE LOGITS
     multipurpose
    1.97
     multifunctional
    1.82
     multifunction
    1.71
     multifaceted
    1.65
     versatile
    1.62
     multitask
    1.52
     comprehensive
    1.49
     versatility
    1.46
     mixed
    1.45
    multif
    1.43
    Activations Density 1.070%

    No Known Activations