© 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-16K
    4. 1226
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and farewells

    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_16k_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
    apath
    1.01
    onaut
    1.00
    aps
    0.99
    rops
    0.98
    #:
    0.97
    ALOG
    0.97
    貨
    0.96
    section
    0.95
    alse
    0.95
    anken
    0.94
    POSITIVE LOGITS
     tirar
    1.53
     convertir
    1.31
     மில்லியன்
    1.29
     dibujar
    1.25
     juta
    1.23
     triệu
    1.22
     मिलियन
    1.22
     infinito
    1.21
    Ꮏ
    1.20
     डालेंगे
    1.19
    Activations Density 0.050%

    No Known Activations