© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 156924
    Prev
    Next
    INDEX
    Explanations

    legal and data privacy matters

    np_acts-logits-general · gemini-2.5-flash-lite

    cannot practicably

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     DriverManager
    0.43
     coups
    0.43
     аў
    0.42
     cultivés
    0.41
    рур
    0.39
     другому
    0.39
     copyrights
    0.39
    醯
    0.38
     mêmes
    0.38
    únior
    0.38
    POSITIVE LOGITS
    हा
    0.51
    hase
    0.49
    Unter
    0.49
     tireless
    0.48
    ず
    0.47
    hse
    0.47
    लम
    0.47
    箪
    0.46
    ح
    0.46
    沒有
    0.46
    Activations Density 0.000%

    No Known Activations