© 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. 9745
    Prev
    Next
    INDEX
    Explanations

    constants and formulas

    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
     STAND
    1.49
     жо
    1.42
     FOOT
    1.34
     ш
    1.33
     王
    1.28
     ט
    1.26
     га
    1.25
     ז
    1.25
     FILES
    1.24
     ра
    1.24
    POSITIVE LOGITS
    nél
    1.23
    uestas
    1.18
    resto
    1.12
    python
    1.03
    nál
    1.02
    Princeton
    1.01
    ambahan
    1.01
    ék
    1.00
    ülete
    1.00
    untuk
    0.99
    Activations Density 0.028%

    No Known Activations