© 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. 14410
    Prev
    Next
    INDEX
    Explanations

    ode to

    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
    ྗ
    2.47
     акций
    2.46
    heder
    2.42
    ྐ
    2.38
     বিপরীত
    2.27
    टक
    2.27
     bouche
    2.25
     przej
    2.24
    yming
    2.22
    íj
    2.21
    POSITIVE LOGITS
    ⁢</
    3.52
    ন
    2.83
    ReLU
    2.78
    िक
    2.77
    IMAL
    2.72
    𝑃
    2.71
    ishly
    2.66
     perce
    2.65
    ಸಿದ
    2.63
     gtag
    2.61
    Activations Density 0.013%

    No Known Activations