© 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. 34-GEMMASCOPE-RES-131K
    7. 56995
    Prev
    Next
    INDEX
    Explanations

    closing html tags

    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_34/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
    ＊＊＊
    -0.95
    }});
    -0.95
     continuare
    -0.93
     می‌توان
    -0.90
    他にも
    -0.90
    Campe
    -0.89
    usen
    -0.88
     hala
    -0.88
     about
    -0.87
      “
    -0.87
    POSITIVE LOGITS
    ᴜ
    1.00
     Bewegung
    1.00
    ↵
    0.98
     lastly
    0.97
    そして
    0.96
     finally
    0.91
     brinde
    0.83
     komt
    0.83
     vejo
    0.83
    ↵↵↵
    0.82
    Activations Density 0.004%

    No Known Activations