© 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. 106639
    Prev
    Next
    INDEX
    Explanations

    returning or reverting to a previous state

    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
    mbangan
    -0.88
    ዚ
    -0.84
    icioso
    -0.79
    
    -0.79
    続きを読む
    -0.77
    bitkan
    -0.77
    guitarra
    -0.77
     Repar
    -0.76
    进来
    -0.75
     родился
    -0.75
    POSITIVE LOGITS
     return
    6.22
    return
    4.88
     returned
    4.72
     returning
    4.66
     Return
    4.47
    Return
    4.38
     returns
    4.16
    Returning
    4.06
     возвра
    4.06
     RETURN
    4.00
    Activations Density 0.123%

    No Known Activations