© 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. 763
    Prev
    Next
    INDEX
    Explanations

    be stored

    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
     I
    1.36
     of
    1.32
     it
    1.31
     you
    1.27
     N
    1.19
     yes
    1.19
     people
    1.15
     It
    1.13
     No
    1.12
     Are
    1.11
    POSITIVE LOGITS
    ක්‍
    1.96
    هد
    1.82
    ermanfaat
    1.81
    affer
    1.80
    قع
    1.79
    راف
    1.76
    <unused1178>
    1.73
    <unused318>
    1.73
    Đặt
    1.72
    Pyrimidine
    1.71
    Activations Density 0.213%

    No Known Activations