© 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. 45477
    Prev
    Next
    INDEX
    Explanations

    Kla words

    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
    ズニー
    -3.23
    珢
    -2.98
    
    -2.98
    メリカ
    -2.91
    萑
    -2.88
    鯢
    -2.86
    纮
    -2.83
    
    -2.70
    ╽
    -2.69
    Ꮉ
    -2.66
    POSITIVE LOGITS
    1
    4.69
    4
    4.09
    9
    4.09
    3
    3.78
    6
    3.53
    8
    3.53
    5
    3.53
    2
    3.17
    7
    3.06
    at
    3.05
    Activations Density 0.005%

    No Known Activations