© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 3802
    Prev
    Next
    INDEX
    Explanations

    come across, comes from, comes with, comes in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
     trasero
    0.89
    𝗮
    0.86
    CommonAncestor
    0.85
    دع
    0.85
    데요
    0.84
     এগুলো
    0.84
    𝘢
    0.83
    )++;
    0.83
    𝑎
    0.80
    𝑖
    0.80
    POSITIVE LOGITS
     forth
    1.52
     out
    1.19
    ตรฐาน
    1.15
     up
    1.14
     ashore
    1.11
     létre
    1.10
     alive
    1.06
     undone
    1.05
    袭
    1.03
    upp
    1.01
    Activations Density 0.023%

    No Known Activations