© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10435
    Prev
    Next
    INDEX
    Explanations

    Rust programming language

    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_22_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
    傣
    1.25
     Jorge
    1.22
     Cancun
    1.21
    Jorge
    1.21
     Cebu
    1.19
    琼
    1.19
    蝎
    1.18
    海南
    1.17
     JavaBean
    1.17
     Yucatan
    1.16
    POSITIVE LOGITS
     mut
    1.58
    rust
    1.53
     Rust
    1.51
     {:?}",
    1.48
    Rust
    1.43
     rust
    1.41
    mut
    1.37
     eprintln
    1.36
    #![
    1.35
     crate
    1.35
    Activations Density 0.016%

    No Known Activations