© 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. 15591
    Prev
    Next
    INDEX
    Explanations

    words starting with Kle

    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
    .’
    -2.75
    我一直
    -2.69
    
    -2.30
    齪
    -2.30
    }$.
    -2.28
     infolge
    -2.27
    
    -2.27
    …’
    -2.27
    彀
    -2.27
    }
    -2.25
    POSITIVE LOGITS
    0
    3.06
    1
    2.69
    and
    2.59
     они
    2.48
     stí
    2.38
    頫
    2.33
    *
    2.33
     bekämp
    2.31
     мои
    2.28
    しちゃ
    2.28
    Activations Density 0.002%

    No Known Activations