© 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. 59080
    Prev
    Next
    INDEX
    Explanations

    respond to

    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
    ◁
    -0.91
    
    -0.85
    δο
    -0.85
     synthèse
    -0.84
    URED
    -0.84
     rengi
    -0.84
     parametro
    -0.84
     dommages
    -0.82
     integran
    -0.81
     Pourquoi
    -0.81
    POSITIVE LOGITS
     with
    1.39
     to
    1.30
     appropriately
    1.05
     quickest
    1.05
     affirm
    0.98
     quicker
    0.96
     by
    0.96
     quickly
    0.94
     accordingly
    0.89
     angem
    0.88
    Activations Density 0.021%

    No Known Activations