© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64732
    Prev
    Next
    INDEX
    Explanations

    software distribution or media

    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
    TableCell
    -0.75
    lag
    -0.74
    OSO
    -0.69
    drawRect
    -0.68
    DESCRIPTION
    -0.68
    CET
    -0.67
     سعيد
    -0.67
     معد
    -0.67
     bar
    -0.67
    Sni
    -0.67
    POSITIVE LOGITS
    zehnten
    0.82
    🤹
    0.78
     MainAxisSize
    0.77
     skips
    0.75
     skip
    0.74
     unchanging
    0.73
    NOWLED
    0.71
    
    0.69
     Linde
    0.68
    グレード
    0.68
    Activations Density 0.018%

    No Known Activations