© 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. 8388
    Prev
    Next
    INDEX
    Explanations

    US, USA, USD

    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
    kező
    0.54
    xy
    0.52
     partial
    0.50
    ্সি
    0.50
    來說
    0.50
    asmuch
    0.49
    戮
    0.49
    termilk
    0.49
     None
    0.48
    terna
    0.48
    POSITIVE LOGITS
     Ush
    0.66
     Serikat
    0.62
    坐标
    0.59
    ウス
    0.58
    urp
    0.58
     यूएस
    0.55
    А
    0.55
    ﴿
    0.55
     quotidien
    0.54
    urious
    0.54
    Activations Density 0.154%

    No Known Activations