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. 3343
    Prev
    Next
    INDEX
    Explanations

    examining causes and consequences

    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
    quad
    1.10
     
    1.09
    it
    1.07
    !
    1.07
     .
    1.00
     car
    0.98
    caps
    0.94
     +
    0.93
    !!
    0.91
      
    0.90
    POSITIVE LOGITS
     이러한
    2.41
    こうした
    2.35
     이런
    2.04
     Erkennt
    2.03
     fenómenos
    2.00
     questões
    1.99
     aceste
    1.99
     iniciativas
    1.97
     perspectivas
    1.96
     compreensão
    1.96
    Activations Density 0.579%

    No Known Activations