© 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. 14289
    Prev
    Next
    INDEX
    Explanations

    resilience

    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
    sa
    2.81
     "@/
    2.33
    реди
    2.30
    Gr
    2.22
    ႇ
    2.18
     ch
    2.15
    esterly
    2.14
     gr
    2.10
    Pr
    2.10
    しくは
    2.07
    POSITIVE LOGITS
    AppDesigner
    3.34
    𝒽
    3.09
    ا
    2.99
    ينا
    2.76
    anço
    2.73
    
    2.71
    า
    2.69
    
    2.69
    hbox
    2.68
    ᒡ
    2.64
    Activations Density 0.013%

    No Known Activations