© 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. 29998
    Prev
    Next
    INDEX
    Explanations

    .posted

    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
    אַ
    -0.77
     various
    -0.75
    捗
    -0.72
    菓
    -0.72
     Gopal
    -0.72
     for
    -0.72
     disparate
    -0.71
    zinho
    -0.71
     сча
    -0.70
    Monty
    -0.70
    POSITIVE LOGITS
    show
    0.95
    strip
    0.95
     게시
    0.93
    testen
    0.93
    穿越
    0.91
    lire
    0.89
    ництва
    0.89
     extre
    0.88
    }},
    0.88
    read
    0.87
    Activations Density 0.010%

    No Known Activations