© 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. 106302
    Prev
    Next
    INDEX
    Explanations

    pragma solidity

    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
    Negative Logits
     rendel
    -0.74
    inama
    -0.69
    ßerdem
    -0.69
    วิ
    -0.68
     propel
    -0.68
    iq
    -0.67
    jom
    -0.66
    cior
    -0.66
    Deliver
    -0.64
     rápidamente
    -0.64
    POSITIVE LOGITS
    assertNot
    0.70
     konuş
    0.69
    Cooperation
    0.69
    herin
    0.69
    Cuatro
    0.68
    𝟯
    0.66
     relleno
    0.65
    бли
    0.65
    帖子
    0.64
    海军
    0.64
    Activations Density 0.058%

    No Known Activations