© 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. 47073
    Prev
    Next
    INDEX
    Explanations

    provided that the following conditions

    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
     income
    -0.73
    роз
    -0.72
    edel
    -0.69
     Biro
    -0.69
    ximate
    -0.68
     purest
    -0.67
    Ronnie
    -0.66
    様が
    -0.65
    Emma
    -0.64
    waterfall
    -0.64
    POSITIVE LOGITS
     shrimps
    0.68
    jvm
    0.67
    lucht
    0.65
    akujem
    0.65
    umbang
    0.64
     ਕ
    0.63
     ע
    0.63
     gelişti
    0.62
    ارش
    0.62
     realizacji
    0.61
    Activations Density 0.088%

    No Known Activations