© 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. 13-GEMMASCOPE-2-RES-16K
    7. 8506
    Prev
    Next
    INDEX
    Explanations

    commend you for doing

    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
     momentarily
    1.21
    brief
    1.17
    orama
    1.10
    =@
    1.09
    equilib
    1.06
     temporarily
    1.06
    iterations
    1.06
     fleeting
    1.05
    rients
    1.05
    truncate
    1.04
    POSITIVE LOGITS
     Kil
    1.19
     disant
    1.04
     K
    1.01
     antig
    1.01
     SAL
    0.98
     Sal
    0.98
     Sall
    0.98
     F
    0.96
     Bandar
    0.96
     olup
    0.94
    Activations Density 0.066%

    No Known Activations