© 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. 56960
    Prev
    Next
    INDEX
    Explanations

    people state v

    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
    แก
    -0.92
     умова
    -0.82
    스터
    -0.79
     ويكي
    -0.78
     fatality
    -0.77
     saman
    -0.76
    Quelques
    -0.75
    ISC
    -0.74
     Folge
    -0.73
    ٹ
    -0.73
    POSITIVE LOGITS
     their
    0.91
     wool
    0.80
     UIButton
    0.79
     tàn
    0.76
    选择了
    0.74
    を設置
    0.74
     taskId
    0.72
     poles
    0.72
     Umwel
    0.72
     Vijay
    0.71
    Activations Density 0.062%

    No Known Activations