© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1893
    Prev
    Next
    INDEX
    Explanations

    conditional logic or preconditions

    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_7_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
     套
    5.18
     也
    5.16
     因此
    4.90
     哦
    4.81
     而且
    4.75
     防止
    4.60
     Ρ
    4.59
     沙
    4.57
     Χ
    4.56
     嗯
    4.55
    POSITIVE LOGITS
    вЂ
    3.59
    untuk
    3.51
    tidak
    3.29
    and
    3.25
    În
    3.13
    Untuk
    3.12
    Tidak
    3.00
    dengan
    2.99
    of
    2.97
    ของ
    2.97
    Activations Density 1.099%

    No Known Activations