© 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. 150
    Prev
    Next
    INDEX
    Explanations

    web links

    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
     ק
    1.62
     ח
    1.59
     При
    1.59
     Lý
    1.56
    ánicos
    1.56
     joyas
    1.54
     Además
    1.53
     ע
    1.53
     Ни
    1.51
     lateribus
    1.50
    POSITIVE LOGITS
     melakukan
    2.43
     tidak
    2.40
     seluruh
    2.34
     untuk
    2.34
     seperti
    2.30
     secara
    2.30
     setelah
    2.28
     memberikan
    2.28
     lebih
    2.24
     sesuai
    2.23
    Activations Density 0.067%

    No Known Activations