© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130191
    Prev
    Next
    INDEX
    Explanations

    falsehoods and inaccuracies

    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
      
    -2.45
     erin
    -2.09
    
    -2.00
     enfant
    -1.95
     fiatal
    -1.93
                
    -1.91
     современных
    -1.88
     целый
    -1.86
     puissant
    -1.82
     enthousi
    -1.82
    POSITIVE LOGITS
    </u>
    2.55
    an
    2.44
    dė
    2.38
    false
    2.36
    er
    2.28
     Behaup
    2.09
    ꜆
    2.08
    是
    2.06
     et
    2.00
     丁目
    1.97
    Activations Density 0.009%

    No Known Activations