© 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. 99021
    Prev
    Next
    INDEX
    Explanations

    burned and its consequences

    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
    er
    -4.22
    en
    -3.67
     nuanced
    -3.23
     prudent
    -2.84
    erintah
    -2.70
     Primarily
    -2.69
     Sufficient
    -2.61
    知名
    -2.58
     Extremely
    -2.55
     Currently
    -2.53
    POSITIVE LOGITS
    臵
    3.50
     แต่
    3.27
    臜
    2.86
     ſmall
    2.75
    pulseira
    2.73
    apatalk
    2.72
    栳
    2.70
     himſelf
    2.61
    ܊
    2.58
    
    2.56
    Activations Density 0.007%

    No Known Activations