© 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. 22-GEMMASCOPE-2-RES-16K
    7. 9730
    Prev
    Next
    INDEX
    Explanations

    simulate

    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_22_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
     strutt
    0.89
    ⓡ
    0.89
    ել
    0.88
     Eso
    0.87
    êu
    0.87
    醤
    0.85
    δί
    0.85
    ষুধ
    0.84
    খন
    0.84
    알
    0.83
    POSITIVE LOGITS
    plicity
    1.51
    ultaneous
    1.33
    ilarly
    1.27
    vastatin
    1.26
    monds
    1.22
    plemente
    1.21
    ulated
    1.19
    ulating
    1.14
    posium
    1.14
    PLIC
    1.13
    Activations Density 0.020%

    No Known Activations