© 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. 127954
    Prev
    Next
    INDEX
    Explanations

    reporting speech

    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
     Some
    -2.17
     in
    -2.16
     Several
    -2.00
     for
    -1.93
     These
    -1.91
     There
    -1.86
     without
    -1.81
     what
    -1.78
     seemingly
    -1.74
     does
    -1.72
    POSITIVE LOGITS
    probably
    1.95
    wasn
    1.91
    began
    1.91
    
    1.88
    described
    1.86
    gives
    1.84
    immediately
    1.82
    mainly
    1.82
    conducted
    1.80
    chose
    1.79
    Activations Density 0.019%

    No Known Activations