© 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. 2672
    Prev
    Next
    INDEX
    Explanations

    in the

    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
     gums
    1.17
     unvaccinated
    1.13
    bing
    1.11
     fucked
    1.10
     messed
    1.09
     ऑफ
    1.07
     inhaling
    1.06
    鸟
    1.06
     wooded
    1.04
     forested
    1.02
    POSITIVE LOGITS
     pamphlet
    1.36
     treatises
    1.31
     publications
    1.25
     Treatise
    1.24
     buku
    1.20
     pamphlets
    1.15
     textbooks
    1.13
    本書
    1.13
     книги
    1.12
     книге
    1.10
    Activations Density 0.423%

    No Known Activations