Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3618
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ,
    1.11
    :
    1.10
    (
    1.01
    йте
    1.00
    /
    0.99
     (
    0.98
     сле
    0.96
     пошу
    0.94
    (''
    0.93
    П
    0.92
    POSITIVE LOGITS
     beneficios
    1.18
    globals
    1.16
     firm
    1.11
     funcionan
    1.07
     berkualitas
    1.06
     seben
    1.05
     gerenci
    1.05
     ezingu
    1.04
     cuál
    1.04
     globally
    1.04
    Activations Density 0.102%

    No Known Activations