© 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. 9577
    Prev
    Next
    INDEX
    Explanations

    lake, lakes, Lago

    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
     Spider
    1.21
    Spider
    1.13
     QRCode
    1.11
     वाय
    1.08
     webbing
    1.07
    쥴
    1.06
     Raquel
    1.01
     hemp
    1.00
     sling
    0.99
    XML
    0.96
    POSITIVE LOGITS
     lake
    3.21
     Lake
    3.19
    Lake
    3.13
     LAKE
    3.02
     lakes
    2.79
     Lakes
    2.66
     lago
    2.65
    lake
    2.65
    湖
    2.58
     lakeside
    2.47
    Activations Density 0.276%

    No Known Activations