© 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. 190
    Prev
    Next
    INDEX
    Explanations

    in and following words

    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
    ,\
    0.88
    online
    0.81
    ,\"
    0.80
    unicorn
    0.78
    ,''
    0.77
    ি
    0.77
     compensate
    0.74
    преде
    0.73
     (\"
    0.72
     accrue
    0.72
    POSITIVE LOGITS
    nhold
    1.03
    엠
    0.86
    ết
    0.85
     accordance
    0.83
    ্ধু
    0.80
    वायरमेंट
    0.78
     целом
    0.78
     spite
    0.77
    quiries
    0.76
    ਸ਼ਨ
    0.76
    Activations Density 1.313%

    No Known Activations