© 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. 12811
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ri
    1.84
    ீன்
    1.41
    おります
    1.40
     modals
    1.39
    s
    1.38
    gri
    1.35
    mals
    1.34
    朢
    1.33
    ों
    1.31
    ির
    1.25
    POSITIVE LOGITS
    י
    1.50
    その
    1.48
    तुरंग
    1.48
    い
    1.48
    𝑨
    1.48
    𝑰
    1.43
     Lieben
    1.41
    𝑳
    1.39
    ない
    1.38
     château
    1.38
    Activations Density 0.028%

    No Known Activations