© 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. 12264
    Prev
    Next
    INDEX
    Explanations

    reading file content

    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
    िखित
    2.47
    esia
    2.39
    ِم
    2.30
    esten
    2.28
    ِد
    2.27
    ُوا
    2.20
    անակ
    2.17
    хам
    2.16
    ücher
    2.15
    年
    2.09
    POSITIVE LOGITS
    ng
    2.86
    फारिश
    2.66
    जिटिव
    2.64
    了
    2.49
    ∑</
    2.48
    ামুটি
    2.40
    张
    2.39
     acom
    2.39
    ड्स
    2.39
    張
    2.37
    Activations Density 0.004%

    No Known Activations