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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8927
    Prev
    Next
    INDEX
    Explanations

    nami

    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
     ترى
    0.88
     منسل
    0.83
    누
    0.81
    freien
    0.81
    混
    0.81
    hein
    0.79
    ّى
    0.79
    唱
    0.79
     NOTICE
    0.78
     yurt
    0.77
    POSITIVE LOGITS
    igh
    1.07
    uttle
    1.03
    undred
    1.02
    appy
    0.99
    IGH
    0.97
    ousing
    0.96
    ockey
    0.95
    arder
    0.90
    olding
    0.90
     ไว้
    0.89
    Activations Density 0.056%

    No Known Activations