© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3973
    Prev
    Next
    INDEX
    Explanations

    code delimiters and variables

    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
    Negative Logits
    쫑
    2.35
    };\
    2.16
    اتھن
    2.14
    ußer
    2.11
    𝓷
    2.11
     quente
    2.07
     harapan
    2.06
    sop
    2.03
    越し
    2.01
    tsó
    1.99
    POSITIVE LOGITS
    iliter
    2.15
    consin
    2.05
    ناسب
    1.97
    ҝ
    1.90
     Override
    1.84
    𝑒
    1.83
     eliminating
    1.82
    iters
    1.81
    ج
    1.81
    ཁ
    1.81
    Activations Density 0.047%

    No Known Activations