© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-65K
    4. 626
    Prev
    Next
    INDEX
    Explanations

    list of lists

    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
    John
    1.72
    ấ
    1.64
    0
    1.61
    year
    1.60
    قام
    1.56
    ierungs
    1.49
    JOHN
    1.49
    レスト
    1.49
    YEAR
    1.49
    estabelecimento
    1.48
    POSITIVE LOGITS
     aesthetic
    1.80
     multifaceted
    1.64
     piti
    1.62
     combining
    1.58
     wisdom
    1.58
     multidis
    1.54
     小
    1.53
     small
    1.53
     mini
    1.53
     cellular
    1.52
    Activations Density 0.152%

    No Known Activations