© 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. 16069
    Prev
    Next
    INDEX
    Explanations

    epigenetic epigenetic epithelial episode epochs

    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
    putString
    0.55
    ريم
    0.54
    ็น
    0.53
    äller
    0.52
     منع
    0.52
     পাইনি
    0.52
    火
    0.52
    置き
    0.51
    См
    0.51
     म्हणतात
    0.50
    POSITIVE LOGITS
     эпи
    1.34
     Ep
    1.32
     ep
    1.30
    Ep
    1.23
     ép
    1.05
     епи
    1.05
     epi
    1.03
     Epoxy
    0.96
     Epi
    0.94
     Epic
    0.93
    Activations Density 0.076%

    No Known Activations