© 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. 59490
    Prev
    Next
    INDEX
    Explanations

    principal

    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
    wegen
    -0.79
     HPC
    -0.77
    tikal
    -0.75
     cubicle
    -0.74
     WEDDING
    -0.74
    ņas
    -0.73
    Biografía
    -0.71
    教授
    -0.71
     borderRadius
    -0.71
    έ
    -0.70
    POSITIVE LOGITS
     principal
    4.41
     Principal
    4.38
    Principal
    4.00
    principal
    3.81
     principals
    3.70
     PRINCIPAL
    3.13
     Principals
    3.02
    PRINCIP
    2.91
    Princip
    2.64
     Principle
    2.47
    Activations Density 0.037%

    No Known Activations