© 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. 11
    Prev
    Next
    INDEX
    Explanations

    model responses to queries

    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
     equally
    2.05
     decidedly
    1.83
     widely
    1.79
     abnormally
    1.76
     这
    1.74
     电
    1.66
    当然
    1.66
     数
    1.62
     体
    1.61
    不断
    1.60
    POSITIVE LOGITS
     på
    2.40
     både
    2.17
     sæ
    2.12
     sammen
    2.06
     flere
    2.04
     tidligere
    2.04
     blandt
    2.01
     hjem
    2.00
     eksempel
    1.99
     lø
    1.99
    Activations Density 0.051%

    No Known Activations