© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14222
    Prev
    Next
    INDEX
    Explanations

    not ... nor

    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
    IRQHandler
    3.12
    とう
    2.96
    }{}
    2.91
    ה
    2.85
    ᅦ
    2.84
    vertx
    2.80
    ở
    2.80
    Có
    2.78
     concurrence
    2.78
    霆
    2.77
    POSITIVE LOGITS
    ‌ای
    2.75
    ायती
    2.62
    zont
    2.54
    okan
    2.53
    р
    2.52
    ಛ
    2.47
    ates
    2.46
    atat
    2.44
    وتا
    2.43
    apar
    2.42
    Activations Density 0.008%

    No Known Activations