© 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. 2295
    Prev
    Next
    INDEX
    Explanations

    greetings like Dear, Hi, Estim

    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
     (+
    1.29
     CCL
    1.28
     DSS
    1.22
     ancillary
    1.22
     SLC
    1.20
     clauses
    1.18
     autos
    1.18
     CSC
    1.17
     seminars
    1.17
     EDS
    1.17
    POSITIVE LOGITS
     oscuridad
    1.26
    作り
    1.23
     dziecka
    1.22
    Tidak
    1.19
    Ș
    1.18
     المُ
    1.16
    のみ
    1.16
    有り
    1.15
    ไม่มี
    1.15
    ยอด
    1.15
    Activations Density 0.306%

    No Known Activations