© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10543
    Prev
    Next
    INDEX
    Explanations

    go to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ytt
    1.04
    ractive
    0.92
    omized
    0.86
    TypeArguments
    0.86
    ImageType
    0.82
    ictionary
    0.81
    copper
    0.81
    瑷
    0.81
    queeze
    0.80
     எண்ணிக்க
    0.80
    POSITIVE LOGITS
     होई
    0.86
     ⓒ
    0.84
     partis
    0.84
     Picard
    0.83
     republic
    0.80
     parr
    0.80
     Warriors
    0.79
     Dali
    0.79
     Wholesale
    0.78
     Wider
    0.77
    Activations Density 0.015%

    No Known Activations