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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 340
    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
     çeşitli
    1.62
     Angaben
    1.50
     registró
    1.48
     पाठ्यक्रमों
    1.45
    ^{\#}\
    1.45
     বিভিন্ন
    1.44
     berbagai
    1.43
     poprzed
    1.42
     tờ
    1.41
    𒉈
    1.40
    POSITIVE LOGITS
     truly
    1.08
     really
    1.07
     desperately
    1.06
     terribly
    1.02
     awfully
    1.00
     nobody
    0.99
     surely
    0.97
     utterly
    0.95
     incapable
    0.89
     REALLY
    0.88
    Activations Density 3.042%

    No Known Activations