© 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. 10256
    Prev
    Next
    INDEX
    Explanations

    lab coat, allow origin

    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
    封
    1.16
     पड़ा
    1.04
     qil
    1.00
    OffsetY
    0.99
     jalan
    0.98
     stopper
    0.97
     sukh
    0.97
     sirven
    0.96
    娑
    0.96
     solucion
    0.96
    POSITIVE LOGITS
     Processes
    0.94
    ANCY
    0.93
    ప్పి
    0.91
    кол
    0.90
     Forms
    0.90
     Presentations
    0.89
     unfiltered
    0.89
    listed
    0.89
    छा
    0.88
     pods
    0.88
    Activations Density 0.002%

    No Known Activations