© 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. 85544
    Prev
    Next
    INDEX
    Explanations

    icon or iconic figures and symbols

    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
    This
    -2.09
    ",
    -2.00
    you
    -1.99
    -"
    -1.98
    ".
    -1.94
     Using
    -1.92
    -
    -1.87
     In
    -1.85
    this
    -1.83
     =
    -1.82
    POSITIVE LOGITS
    
    2.16
    寕
    2.14
     gewel
    1.96
    aimeJ
    1.92
     pazi
    1.91
    錞
    1.84
    餍
    1.83
     berdua
    1.80
     จาก
    1.80
     تعرض
    1.79
    Activations Density 0.007%

    No Known Activations