© 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-65K
    7. 883
    Prev
    Next
    INDEX
    Explanations

    code structure keywords

    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_65k_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
     آ
    1.70
     brutal
    1.67
     ا
    1.67
     Ō
    1.64
     Calories
    1.62
     Providing
    1.62
     因此
    1.62
     ر
    1.61
     Μ
    1.60
     وح
    1.59
    POSITIVE LOGITS
     contador
    1.21
     mesmo
    1.10
     deputado
    1.09
     stesse
    1.09
     smlou
    1.08
    izace
    1.04
     ktor
    1.02
     చేసింది
    0.98
     prefeito
    0.98
     delegado
    0.97
    Activations Density 0.153%

    No Known Activations