© 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. 12-GEMMASCOPE-2-RES-16K
    7. 8933
    Prev
    Next
    INDEX
    Explanations

    **Engaging with tasks**

    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_12_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
     forcément
    1.02
    nson
    0.96
    思議
    0.93
    ংখ্যান
    0.90
    ڍ
    0.90
    olated
    0.89
     ponctu
    0.89
    ClearedBy
    0.89
    伝える
    0.88
    ［
    0.88
    POSITIVE LOGITS
    s
    1.38
    1
    1.18
    ्स
    1.12
     muut
    1.09
    ς
    1.08
    ee
    1.05
    }'
    1.05
    
    1.05
     Pari
    1.04
    3
    1.04
    Activations Density 0.542%

    No Known Activations