© 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. 18916
    Prev
    Next
    INDEX
    Explanations

    tells the browser

    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
     trai
    0.93
     👀
    0.92
     berätt
    0.87
     everyone
    0.86
     pushing
    0.86
     fler
    0.86
     meet
    0.84
     nghiệm
    0.84
     bring
    0.84
     👉
    0.83
    POSITIVE LOGITS
    એ
    1.10
    bold
    1.03
    www
    1.01
    EDB
    1.00
    Microsoft
    1.00
    UH
    0.94
    microsoft
    0.93
    BOARD
    0.93
    ongoing
    0.93
    database
    0.91
    Activations Density 0.001%

    No Known Activations