© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 39
    Prev
    Next
    INDEX
    Explanations

    its purpose and existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     結果
    0.60
     构建
    0.58
     緊急
    0.58
     其中
    0.58
     开始
    0.57
     細
    0.56
     事件
    0.54
     通知
    0.53
    DriverManager
    0.53
     人気
    0.53
    POSITIVE LOGITS
     own
    1.57
     OWN
    1.12
     respective
    1.01
    own
    1.01
     Own
    0.99
     rightful
    0.95
     destiny
    0.86
     eigenen
    0.86
     countrymen
    0.85
     собственные
    0.84
    Activations Density 1.624%

    No Known Activations