© 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. 1942
    Prev
    Next
    INDEX
    Explanations

    conditional logic and alternatives

    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
    awak
    1.09
    君
    1.04
    paper
    1.02
    rn
    1.01
    beg
    1.01
    root
    1.00
    houn
    0.97
    esc
    0.97
    borne
    0.95
    幕
    0.95
    POSITIVE LOGITS
     autres
    1.70
     else
    1.70
     diğer
    1.62
     outras
    1.56
     innym
    1.49
     sonst
    1.42
     otras
    1.42
     başka
    1.40
     différences
    1.40
     pozosta
    1.40
    Activations Density 0.027%

    No Known Activations