© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9773
    Prev
    Next
    INDEX
    Explanations

    don't feel like or pressured

    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
     getNode
    1.08
    嚏
    1.03
    дик
    1.02
    ^{*}$.
    1.02
    悳
    1.00
     HOWEVER
    0.99
     한다는
    0.97
     собственно
    0.96
    悉
    0.94
     *)
    0.94
    POSITIVE LOGITS
    Orden
    0.87
    定番
    0.86
    enta
    0.84
    ∼
    0.79
     eta
    0.79
     Naina
    0.78
    जिला
    0.78
     terkenal
    0.77
    Delayed
    0.77
     Magazines
    0.77
    Activations Density 0.004%

    No Known Activations