© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9322
    Prev
    Next
    INDEX
    Explanations

    embedding and its use

    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
     baloncesto
    1.22
     satan
    1.21
     Vacation
    1.20
     Yaz
    1.19
     Punch
    1.16
     sanat
    1.16
     alot
    1.16
    俗
    1.14
    avanje
    1.13
     asthma
    1.12
    POSITIVE LOGITS
    њи
    1.02
     کی
    1.01
    МИ
    1.01
    Inde
    1.00
    О
    0.98
    Ти
    0.96
    Ка
    0.95
    働
    0.95
    GI
    0.94
    мою
    0.94
    Activations Density 0.008%

    No Known Activations