© 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. 8491
    Prev
    Next
    INDEX
    Explanations

    SQL column types and definitions

    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
     abut
    0.86
    აწილ
    0.84
    frid
    0.81
     lest
    0.81
    qid
    0.81
    ¬
    0.78
    vital
    0.77
    —
    0.76
     merchandise
    0.76
     discharges
    0.76
    POSITIVE LOGITS
    舧
    1.47
     swojego
    1.46
     bagus
    1.42
    肨
    1.41
     strategia
    1.39
    
    1.38
     jakarta
    1.38
     Sparkling
    1.38
    🌏
    1.37
    漼
    1.37
    Activations Density 0.021%

    No Known Activations