© 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. 38053
    Prev
    Next
    INDEX
    Explanations

    Farah, Fakhri, Akhtar names

    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
    gpa
    -0.73
     cabe
    -0.71
     numero
    -0.71
     posicion
    -0.71
     melan
    -0.69
    posterior
    -0.69
     gab
    -0.69
     submitted
    -0.68
    cabe
    -0.68
    
    -0.68
    POSITIVE LOGITS
    Finally
    0.77
     Athene
    0.77
     FH
    0.75
    issimi
    0.75
     Finally
    0.73
    եռ
    0.73
     increments
    0.71
     Kollegen
    0.71
    duplex
    0.71
     Occasionally
    0.70
    Activations Density 0.016%

    No Known Activations