© 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. 10553
    Prev
    Next
    INDEX
    Explanations

    Aut followed by related endings

    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
     ৩৬
    0.99
     Dre
    0.97
     অপরা
    0.94
     ۳
    0.91
    สาม
    0.90
     Fran
    0.89
     Thirty
    0.88
     Mooney
    0.88
     おり
    0.87
    독
    0.87
    POSITIVE LOGITS
    rierung
    0.94
     localización
    0.91
    皇家
    0.90
    alc
    0.89
     conceitos
    0.88
    রাত
    0.88
     fallo
    0.88
     capilla
    0.87
     pedra
    0.87
     senador
    0.86
    Activations Density 0.003%

    No Known Activations