© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10352
    Prev
    Next
    INDEX
    Explanations

    We can action

    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_22_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
     ofthe
    1.20
    ofthe
    1.14
    primarily
    1.01
     additionally
    0.88
     principally
    0.87
     thing
    0.86
    ᄈ
    0.85
    ِلِّ
    0.84
     primarily
    0.83
    of
    0.83
    POSITIVE LOGITS
     ਇੱਕ
    1.29
     ایک
    1.26
     ένα
    1.25
     هذا
    1.24
     واحد
    1.22
     السيارة
    1.17
     أحد
    1.16
     آخر
    1.15
     μια
    1.14
     ابن
    1.12
    Activations Density 0.001%

    No Known Activations