© 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. 107957
    Prev
    Next
    INDEX
    Explanations

    Gibson Les Paul guitars

    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
     gend
    -0.78
    GUIDE
    -0.77
    direkt
    -0.76
    frist
    -0.76
     Transplantation
    -0.75
     rekom
    -0.74
     noce
    -0.73
     rolle
    -0.73
    Acetone
    -0.73
    Ambiente
    -0.71
    POSITIVE LOGITS
     locking
    0.96
     shred
    0.91
    亻
    0.90
     hyd
    0.85
    Ss
    0.81
    Bitmap
    0.79
    onesia
    0.78
     تتم
    0.75
     đình
    0.74
     autofocus
    0.74
    Activations Density 0.006%

    No Known Activations