© 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. 13-GEMMASCOPE-2-RES-16K
    7. 4781
    Prev
    Next
    INDEX
    Explanations

    way a

    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_13_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
     dagegen
    1.07
    äng
    1.06
    大幅
    1.05
     সংখ্যাগ
    1.02
     untenable
    1.00
     erő
    1.00
    Incremental
    0.99
    铳
    0.99
     przede
    0.99
     unsur
    0.98
    POSITIVE LOGITS
     можете
    1.17
     you
    1.14
     could
    1.09
    could
    1.08
    you
    1.06
    สามารถ
    1.02
     สามารถ
    0.96
     Puede
    0.95
     walked
    0.94
     подой
    0.94
    Activations Density 0.097%

    No Known Activations