© 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. 14515
    Prev
    Next
    INDEX
    Explanations

    nationalism and identity

    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
     programmatic
    2.24
    🏻
    2.18
    nés
    2.11
    ণিত
    1.98
     Normdatei
    1.97
     condado
    1.94
    🏼
    1.93
    cat
    1.91
    onnées
    1.91
     fondamentali
    1.88
    POSITIVE LOGITS
    طان
    1.85
    ط
    1.83
    isty
    1.80
    amon
    1.80
     consci
    1.77
    ів
    1.69
    魂
    1.67
    м
    1.66
    istical
    1.66
    uose
    1.66
    Activations Density 0.011%

    No Known Activations