© 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. 128653
    Prev
    Next
    INDEX
    Explanations

    object access with dot

    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
     that
    -2.34
     During
    -2.33
     but
    -2.16
     While
    -2.06
     even
    -2.06
     даже
    -1.98
     regarding
    -1.98
     or
    -1.98
     which
    -1.93
     Even
    -1.87
    POSITIVE LOGITS
     horloge
    2.06
     serre
    1.92
     noirs
    1.92
     ché
    1.90
    
    1.89
     pè
    1.88
     concours
    1.88
     barres
    1.87
     inox
    1.83
     boute
    1.80
    Activations Density 0.007%

    No Known Activations