© 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. 13-GEMMASCOPE-2-RES-16K
    7. 15684
    Prev
    Next
    INDEX
    Explanations

    parent node, modern design, climatic

    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_13_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
     MACH
    1.19
     enzymes
    1.14
     radicals
    1.12
     Machines
    1.12
     Neh
    1.11
    場所に
    1.09
    几
    1.08
     শ্
    1.07
     Enzymes
    1.07
     Horde
    1.06
    POSITIVE LOGITS
    Trailing
    1.15
    MsgCallBack
    1.13
    든지
    1.13
    ეგი
    1.11
     dira
    1.08
    Banco
    1.08
    pageToken
    1.06
    िड
    1.06
    ائدة
    1.06
    dashboard
    1.06
    Activations Density 0.000%

    No Known Activations