© 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-16K
    7. 919
    Prev
    Next
    INDEX
    Explanations

    in "$ string assignment

    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_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
     create
    0.83
     Chocolate
    0.81
     creating
    0.76
     Initialize
    0.75
     password
    0.73
     Create
    0.70
    ,
    0.70
     initialize
    0.70
     simplifying
    0.69
     chocolate
    0.68
    POSITIVE LOGITS
    iksaan
    0.94
     motionProxy
    0.92
     circunstancias
    0.89
     গিয়া
    0.89
     guzt
    0.89
     fillColorSpace
    0.89
    liono
    0.88
    畸
    0.88
    ্ডিং
    0.88
    ionante
    0.88
    Activations Density 0.636%

    No Known Activations