© 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. 86
    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
     当
    1.73
     その
    1.65
    郑
    1.53
     无
    1.52
     温
    1.47
    企业
    1.43
     与
    1.42
     黄
    1.42
     电
    1.41
     学
    1.40
    POSITIVE LOGITS
     för
    2.56
     två
    2.39
     åter
    2.36
     över
    2.34
     även
    2.32
     från
    2.32
     första
    2.26
     många
    2.26
     utveck
    2.25
     några
    2.25
    Activations Density 0.069%

    No Known Activations