© 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. 9908
    Prev
    Next
    INDEX
    Explanations

    Asegúrate

    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
     感
    1.01
     climate
    0.98
     全
    0.98
     पुराने
    0.94
     fortified
    0.92
    脌
    0.90
     森
    0.89
     Ν
    0.88
     harrowing
    0.88
     stripped
    0.88
    POSITIVE LOGITS
    astos
    1.19
    kar
    1.11
    inh
    1.09
    czek
    1.05
    dul
    1.04
    uus
    1.02
    hah
    1.01
    kas
    1.01
    p
    1.00
    verify
    0.99
    Activations Density 0.005%

    No Known Activations