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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103653
    Prev
    Next
    INDEX
    Explanations

    PDT, US, value

    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
    anwalt
    -0.80
    🄽
    -0.74
     potest
    -0.73
     fondu
    -0.72
     organics
    -0.72
     microfibra
    -0.72
    jemy
    -0.71
     DPRD
    -0.69
    ناصر
    -0.69
    ciado
    -0.69
    POSITIVE LOGITS
     canvas
    1.00
    canvas
    0.95
     card
    0.84
    idenza
    0.83
     platform
    0.82
     Canvas
    0.81
    copyWith
    0.79
     bright
    0.79
    brightness
    0.79
    platform
    0.79
    Activations Density 0.001%

    No Known Activations