© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2762
    Prev
    Next
    INDEX
    Explanations

    stands for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
    แมนเชสเตอร์ซิตี
    0.82
    <unused626>
    0.81
    اویز
    0.80
     Sedangkan
    0.79
    퇸
    0.78
    ِمض
    0.77
    <unused228>
    0.75
     பாரன்ஹீ
    0.75
    <unused1172>
    0.74
     podamos
    0.74
    POSITIVE LOGITS
     […]
    0.58
    -
    0.58
    <eos>
    0.57
    {
    0.55
    ν
    0.54
     {
    0.52
    ‌
    0.52
    ↵
    0.51
     –
    0.50
    ​
    0.49
    Activations Density 0.065%

    No Known Activations