© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65744
    Prev
    Next
    INDEX
    Explanations

    actually, contrary, but

    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
     también
    -1.08
     também
    -1.05
     также
    -1.01
    也很
    -1.00
     différences
    -0.92
    räck
    -0.91
     також
    -0.90
    haled
    -0.89
     évidemment
    -0.89
     alters
    -0.89
    POSITIVE LOGITS
    反而
    2.33
     actually
    2.08
     наоборот
    1.91
    むしろ
    1.86
     justru
    1.75
     malah
    1.67
    逆に
    1.66
     juist
    1.66
     דו
    1.63
     parado
    1.57
    Activations Density 0.094%

    No Known Activations