© 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. 425
    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
     personer
    0.87
     seus
    0.85
     rumores
    0.82
    iss
    0.81
     berikut
    0.81
     suoi
    0.80
     والم
    0.79
    佢
    0.78
    ByCategory
    0.77
     dessen
    0.76
    POSITIVE LOGITS
     own
    2.33
     favorite
    1.54
     OWN
    1.48
     favourite
    1.47
     Own
    1.44
     propre
    1.35
     propres
    1.35
     beloved
    1.30
     newfound
    1.28
    own
    1.27
    Activations Density 3.198%

    No Known Activations