© 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. 1430
    Prev
    Next
    INDEX
    Explanations

    find a or the

    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
    DrawerToggle
    2.24
    iž
    2.00
    md
    1.96
    пор
    1.92
    膚
    1.87
     لە
    1.87
    ty
    1.86
     از
    1.85
    czyn
    1.83
    cznej
    1.83
    POSITIVE LOGITS
     solve
    2.48
     evade
    2.47
     chauss
    2.46
    amentals
    2.37
     explore
    2.34
    amental
    2.34
     find
    2.34
     eliminate
    2.33
    ॅमिली
    2.33
     minimize
    2.32
    Activations Density 0.545%

    No Known Activations