© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 83694
    Prev
    Next
    INDEX
    Explanations

    Palo Alto, Kotzin, Verdan, glycol, Dolby, Hokuri

    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
    Negative Logits
     They
    -3.50
     --
    -3.33
    ↵↵
    -3.06
     -
    -3.05
     So
    -3.03
    ↵
    -3.00
     That
    -2.97
    0
    -2.89
     —
    -2.80
    w
    -2.72
    POSITIVE LOGITS
    幛
    3.67
     desembar
    3.28
    釭
    3.25
    ㈮
    3.19
    냑
    3.16
    
    3.08
    ⎔
    2.98
     tradis
    2.97
     abbildung
    2.95
    ꯲
    2.95
    Activations Density 0.010%

    No Known Activations