© 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. 10135
    Prev
    Next
    INDEX
    Explanations

    numbered explanation points

    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
    槿
    1.01
    ($_
    0.99
     Malik
    0.97
     TNI
    0.97
     catholique
    0.97
     Lore
    0.96
     Maulana
    0.94
     musul
    0.94
    SUN
    0.94
    ﷲ
    0.91
    POSITIVE LOGITS
    壓力
    0.98
     pressure
    0.98
    pressure
    0.96
     PRESSURE
    0.94
     Engine
    0.92
     Pressure
    0.92
    压力
    0.92
     Bloch
    0.91
     silic
    0.91
    engine
    0.91
    Activations Density 0.026%

    No Known Activations