© 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. 62395
    Prev
    Next
    INDEX
    Explanations

    hayes hayter hayward

    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
    大さじ
    -0.93
     Filippo
    -0.85
     👆
    -0.81
     xiii
    -0.80
     Futebol
    -0.79
     pavillon
    -0.78
    🤣🤣🤣
    -0.77
     <<<
    -0.77
     octobre
    -0.77
     آب
    -0.76
    POSITIVE LOGITS
    📏
    0.88
    ]$.
    0.84
    HAY
    0.79
    也许
    0.75
    AAAAA
    0.75
    maría
    0.74
     świe
    0.74
    ୭
    0.73
    ceiver
    0.73
    ckle
    0.72
    Activations Density 0.021%

    No Known Activations