© 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. 7-GEMMASCOPE-2-RES-16K
    7. 8
    Prev
    Next
    INDEX
    Explanations

    *

    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_7_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
     №
    1.24
     城
    1.21
    天堂
    1.10
     मुंबई
    1.10
     не
    1.09
     (?
    1.08
     за
    1.06
     пи
    1.06
    ⠿
    1.05
     和
    1.04
    POSITIVE LOGITS
    dependencies
    0.96
    twig
    0.90
    things
    0.85
    $\
    0.84
    
    0.82
    asses
    0.82
    tare
    0.81
    individual
    0.80
    𝐭
    0.80
    arnings
    0.79
    Activations Density 0.291%

    No Known Activations