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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 15215
    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
     round
    1.00
     বাধা
    0.94
     acquiring
    0.91
     unlaw
    0.91
     slicing
    0.89
    s
    0.88
     ordinances
    0.88
    显示
    0.87
     shearing
    0.85
    Round
    0.85
    POSITIVE LOGITS
    wachung
    1.21
     unattended
    1.16
     தினத்தன்று
    1.12
    ดูแล
    1.10
    괄
    1.08
    valment
    1.05
     nở
    1.03
    ರುತ್ತ
    1.03
     laissent
    1.02
     nyug
    1.02
    Activations Density 0.144%

    No Known Activations