© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117250
    Prev
    Next
    INDEX
    Explanations

    financial, technical, and diverse content

    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
    司法
    -0.82
    射手
    -0.79
    뼈
    -0.77
    edì
    -0.75
    stone
    -0.74
    יסטוריה
    -0.73
    美的
    -0.71
     än
    -0.71
     Shine
    -0.70
     Anwendungs
    -0.70
    POSITIVE LOGITS
     împ
    0.81
    ยาย
    0.79
     Tapes
    0.78
    大満足
    0.74
     NSObject
    0.74
    whence
    0.73
    entyfik
    0.71
     souligne
    0.71
    JButton
    0.71
     JLabel
    0.71
    Activations Density 0.001%

    No Known Activations