© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 95522
    Prev
    Next
    INDEX
    Explanations

    also, likewise, too

    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_22/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
     that
    -1.20
     which
    -1.13
     and
    -0.94
     the
    -0.93
     therefore
    -0.85
    ']))
    -0.81
    就像
    -0.81
    =".$
    -0.79
    ():
    
    -0.79
     then
    -0.79
    POSITIVE LOGITS
     ebenso
    1.88
     وكذلك
    1.68
     וגם
    1.59
     aswell
    1.57
     Ebenso
    1.56
     επίσης
    1.56
     также
    1.49
     نیز
    1.40
     також
    1.38
     también
    1.34
    Activations Density 0.071%

    No Known Activations