© 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. 15487
    Prev
    Next
    INDEX
    Explanations

    coefficients and sequences

    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
     ainsi
    1.09
     glucose
    1.03
     así
    0.98
    ocado
    0.97
     grâce
    0.94
     ¡
    0.92
     hockey
    0.91
     courte
    0.90
     Hockey
    0.89
     court
    0.88
    POSITIVE LOGITS
    َد
    0.95
    parametri
    0.93
    𝙉
    0.92
    parameter
    0.91
     parameterized
    0.89
    َرَ
    0.89
     Вене
    0.89
    न्दावन
    0.87
    ListOf
    0.86
    𝑫
    0.86
    Activations Density 0.040%

    No Known Activations