© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81267
    Prev
    Next
    INDEX
    Explanations

    proposed development

    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
    isseaux
    -0.87
    かもしれない
    -0.84
     neighborhood
    -0.82
     qualified
    -0.81
     hatta
    -0.79
     neighborhoods
    -0.78
    ratore
    -0.78
    Şi
    -0.78
     美食
    -0.77
     Regionen
    -0.77
    POSITIVE LOGITS
    urma
    0.94
     dwelling
    0.88
     Employees
    0.87
    quoi
    0.84
     rear
    0.83
    guise
    0.82
     polega
    0.81
    ámb
    0.81
     employees
    0.80
    Existing
    0.80
    Activations Density 0.005%

    No Known Activations