© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2789
    Prev
    Next
    INDEX
    Explanations

    set out or set forth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Juri
    -0.97
    جوايز
    -0.80
    ウィキ
    -0.79
    Gore
    -0.77
     бокс
    -0.76
    Schwer
    -0.76
    انواع
    -0.76
    
    -0.75
    PopupWindow
    -0.74
    Btw
    -0.73
    POSITIVE LOGITS
     set
    3.13
    set
    2.16
    Set
    2.03
     Set
    1.91
    SET
    1.82
     SET
    1.71
     sets
    1.64
    セット
    1.47
     setzte
    1.29
     gesetzt
    1.24
    Activations Density 0.057%

    No Known Activations