© 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. 10-GEMMASCOPE-RES-131K
    7. 73390
    Prev
    Next
    INDEX
    Explanations

    if this opinion

    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_10/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
     capuz
    -1.62
     artesanato
    -1.59
    냑
    -1.55
    やっぱり
    -1.50
     manteiga
    -1.49
    \}}
    -1.48
     hade
    -1.48
     senhora
    -1.47
     molho
    -1.47
    奁
    -1.46
    POSITIVE LOGITS
     you
    2.23
     with
    1.97
     or
    1.95
     from
    1.88
     at
    1.84
     operations
    1.73
     if
    1.59
     wensen
    1.57
     there
    1.54
     ontdek
    1.50
    Activations Density 0.131%

    No Known Activations