© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    scope global

    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
    𝚒
    2.55
    𝚎
    2.40
    KindOfClass
    2.40
    উ
    2.32
    𝚘
    2.29
    प्ताह
    2.26
    𝚑
    2.23
    िर
    2.18
    𝐖
    2.17
    antes
    2.17
    POSITIVE LOGITS
    e
    4.61
    加坡
    4.25
    ে
    4.23
    ੀ
    3.94
    י
    3.79
    יים
    3.78
    eer
    3.71
    ০
    3.66
    a
    3.62
    eers
    3.54
    Activations Density 0.013%

    No Known Activations