© 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. 3386
    Prev
    Next
    INDEX
    Explanations

    i686, LPC, US79KUA, 8812A

    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
     bl
    -0.73
    ambo
    -0.72
    🚵
    -0.71
    𝑧
    -0.69
     potest
    -0.68
     Bologna
    -0.68
     Chính
    -0.68
    𝑞
    -0.66
    が届
    -0.66
    anye
    -0.66
    POSITIVE LOGITS
    jail
    0.77
     vitória
    0.77
    PerPage
    0.77
     množství
    0.75
     Poli
    0.75
    volles
    0.74
    urop
    0.74
    Poli
    0.74
     вжи
    0.73
    ólica
    0.73
    Activations Density 0.019%

    No Known Activations