© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18675
    Prev
    Next
    INDEX
    Explanations

    sed substitution command

    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
    㑨
    0.87
     MoU
    0.85
     ჩატი
    0.84
     tứ
    0.82
    𐰼
    0.81
     Texts
    0.80
    openList
    0.80
    ាន
    0.80
     tanah
    0.80
     fudai
    0.79
    POSITIVE LOGITS
     about
    0.66
    about
    0.58
     pec
    0.58
    Sim
    0.57
     Yellow
    0.57
     =
    0.56
     опреде
    0.56
     >
    0.56
     for
    0.56
     much
    0.55
    Activations Density 0.006%

    No Known Activations