© 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. 71867
    Prev
    Next
    INDEX
    Explanations

    software components and projects

    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
     kapture
    -1.83
    seems
    -1.71
     dát
    -1.70
    ਗ਼
    -1.63
     SEVER
    -1.61
     naï
    -1.58
    
    -1.57
    seem
    -1.57
    ܞ
    -1.56
     QUICK
    -1.55
    POSITIVE LOGITS
     or
    2.86
     at
    2.20
     which
    1.96
     или
    1.87
     may
    1.84
     regarding
    1.81
     just
    1.77
     If
    1.75
     if
    1.70
     that
    1.68
    Activations Density 0.025%

    No Known Activations