© 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. 1960
    Prev
    Next
    INDEX
    Explanations

    https://

    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
     verbal
    1.51
     legitim
    1.50
     tic
    1.41
     overtly
    1.38
     delicate
    1.37
    -,
    1.36
     fren
    1.34
     nine
    1.34
     hinder
    1.33
     demonstr
    1.32
    POSITIVE LOGITS
    addContainerGap
    1.74
    Setelah
    1.55
    ễ
    1.54
    さて
    1.53
    สำหรับ
    1.52
    ě
    1.44
    Jika
    1.43
    Columns
    1.42
    ínű
    1.41
    Jangan
    1.39
    Activations Density 0.003%

    No Known Activations