© 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. 574
    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_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
     अपेक्षाकृत
    1.27
    常用的
    1.22
    只好
    1.20
     dodgy
    1.19
    回避
    1.19
    躲
    1.18
    ទំនង
    1.18
     sedative
    1.17
     মোটামুটি
    1.17
    😦
    1.16
    POSITIVE LOGITS
     dedication
    1.86
     commitment
    1.77
     unwavering
    1.63
     passion
    1.59
     mission
    1.59
     committed
    1.58
     Commitment
    1.56
     values
    1.53
     passionate
    1.52
     visionary
    1.51
    Activations Density 5.084%

    No Known Activations