© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    **2.**

    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
    Relationships
    0.96
    Organic
    0.94
    ClNO
    0.94
    COCH
    0.94
     Relationships
    0.90
     கரிம
    0.90
    ܝ
    0.89
    Rita
    0.89
    relationship
    0.89
    មុ
    0.89
    POSITIVE LOGITS
     stabilizers
    1.14
     stabilizer
    1.03
     stabilizing
    1.01
    増
    1.01
     stabil
    1.00
    膨
    0.96
    stabil
    0.94
     загу
    0.94
     artificial
    0.91
     Artificial
    0.88
    Activations Density 0.162%

    No Known Activations