© 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. 17-GEMMASCOPE-2-RES-16K
    7. 117
    Prev
    Next
    INDEX
    Explanations

    based on data and algorithms

    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_17_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
    ⁣
    1.47
    ⁣⁣
    1.39
     royals
    1.35
     Vikings
    1.35
     paramedics
    1.34
     reimag
    1.33
     ‍
    1.32
    Loy
    1.32
     ­
    1.31
     titans
    1.31
    POSITIVE LOGITS
    ；
    1.55
     있다
    1.36
    는다
    1.30
     것이다
    1.30
     obtains
    1.26
    得到
    1.25
     것
    1.22
     것에
    1.21
    것
    1.21
    因而
    1.19
    Activations Density 0.197%

    No Known Activations