© 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. 160878
    Prev
    Next
    INDEX
    Explanations

    politics and power

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

    German formal address

    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
     TECHNICAL
    0.46
    /}
    0.44
    もちろん
    0.44
    写入
    0.44
     যদি
    0.44
    esorios
    0.44
     NOMBRE
    0.43
    <0x0D>
    0.42
     長
    0.42
    のかな
    0.42
    POSITIVE LOGITS
    जेक्शन
    0.51
     gastroenter
    0.47
     manslaughter
    0.47
     lekar
    0.44
     horn
    0.44
     tavern
    0.43
    uelle
    0.43
     tych
    0.43
     способности
    0.42
     navy
    0.42
    Activations Density 0.001%

    No Known Activations